Neural Network Model Research Articles

Intelligent Pressure Monitoring Method of BP Neural Network Optimized by Genetic Algorithm: A Case Study of X Well Area in Yinggehai Basin

While drilling formation pressure monitoring is an important basis for ensuring drilling safety and oil and gas discovery, the calculation of existing pressure monitoring methods is complicated and the accuracy is difficult to improve. Taking the actual well data of well area X in Yinggehai Basin as the object, correlation analysis was first carried out to select and standardize the data features, and relevant effective parameters were extracted. Two kinds of neural networks, back-propagation network BP and back-propagation network GA-BP optimized by genetic algorithm, were used to establish artificial intelligence monitoring models of formation pressure based on 10 kinds of measuring and logging data, respectively. The application effect of the model was evaluated based on the results of monitoring the pressure while drilling. The results show that the monitoring accuracy of the BP neural network model is 91.25%, and that of the GA-BP neural network model is 92.89%. The latter has a better monitoring effect on formation pore pressure. In formation pressure monitoring in areas with a high degree of well control, the introduction of artificial intelligence technology has the advantages of simplicity, speed and high precision, and can provide a reference for other areas of pressure monitoring while drilling.

Evaluating Advanced Machine Learning Models for Histopathological Diagnosis of Hansen Disease.

Leprosy is a neglected infectious disease caused by Mycobacterium leprae and Mycobacterium lepromatosis and remains a public health challenge in tropical regions. Therefore, the development of technological tools such as machine learning (ML) offers an opportunity to innovate strategies for improving the diagnosis of this complex disease. To validate the utility of different ML models for the histopathological diagnosis of Hansen disease. An observational study was conducted where 55 H&E-stained tissue slides from leprosy patients and 51 healthy skin controls were analyzed using microphotographs captured at various magnifications. These images were categorized based on histopathological findings and processed using the Cross-Industry Standard Process for Data Mining methodology for designing and training ML models. Five types of ML models were evaluated using standard metrics such as accuracy, sensitivity, and specificity, emphasizing data normalization as a fundamental step in optimizing model performance. The artificial neural network (ANN) model demonstrated an accuracy of 70%, sensitivity of 74%, and specificity of 65%, demonstrating its ability to identify leprosy cases with moderate precision. The receiver operating characteristic curve of the ANN model showed an area under the curve of 0.71. Conversely, models such as decision trees, logistic regression, and random forests showed similar accuracy results but with slightly lower sensitivity, potentially indicating a higher risk of false negatives in detecting leprosy-positive cases. The ANN model emerges as a promising alternative for leprosy detection. However, further refinement of these models is necessary to enhance their adaptability across different clinical settings and participation in patient care.

Using spatial video and deep learning for automated mapping of ground-level context in relief camps.

The creation of relief camps following a disaster, conflict or other form of externality often generates additional health problems. The density of people in a highly stressed environment with questionable safe food and water access presents the potential for infectious disease outbreaks. These camps are also not static data events but rather fluctuate in size, composition, and level and quality of service provision. While contextualized geospatial data collection and mapping are vital for understanding the nature of these camps, various challenges, including a lack of data at the required spatial or temporal granularity, as well as the issue of sustainability, can act as major impediments. Here, we present the first steps toward a deep learning-based solution for dynamic mapping using spatial video (SV). We trained a convolutional neural network (CNN) model on a SV dataset collected from Goma, Democratic Republic of Congo (DRC) to identify relief camps from video imagery. We developed a spatial filtering approach to tackle the challenges associated with spatially tagging objects such as the accuracy of global positioning system and positioning of camera. The spatial filtering approach generates smooth surfaces of detection, which can further be used to capture changes in microenvironments by applying techniques such as raster math. The initial results suggest that our model can detect temporary physical dwellings from SV imagery with a high level of precision, recall, and object localization. The spatial filtering approach helps to identify areas with higher concentrations of camps and the web-based tool helps to explore these areas. The longitudinal analysis based on applying raster math on the detection surfaces revealed locations, which had a considerable change in the distribution of tents over space and time. The results lay the groundwork for automated mapping of spatial features from imagery data. We anticipate that this work is the building block for a future combination of SV, object identification and automatic mapping that could provide sustainable data generation possibilities for challenging environments such as relief camps or other informal settlements.

Efficient High Heating Value estimation using Latin Hypercube Sampling and Artificial Neural Network-based approach.

To maximize energy recovery in waste-to-energy (WTE) systems, the High Heating Value (HHV) of municipal solid waste (MSW) must be accurately estimated. To forecast the HHV of MSW, this study proposes a unique method that combines an Artificial Neural Network (ANN) model with Latin Hypercube Sampling (LHS), with a focus on Solan City, Himachal Pradesh, India. In the present study, the elemental characteristics of waste have been used to deal with uncertainty and to find the suitable parameters responsible for the HHV of the MSW. Initially, Latin Hypercube Sampling (LHS) has been used to deal with uncertainty in the elemental composition of MSW, which includes carbon (C), hydrogen (H), nitrogen (N), sulfur (S), and oxygen (O) content. This elemental composition has been used as input parameters to the ANN model for predicting the HHV of MSW. The network 5-28-5-1 offered a minimum MAPE value of 2.18%, MSE, RMSE and R2 values are 0.012, 0.107 and 0.767, respectively. Thereafter, a synaptic weight approach was used to find the most significant parameters responsible for HHV in MSW. It was observed that carbon is the most suitable parameter for HHV of MSW. By dealing with the uncertainty in MSW characteristics, the integration of LHS strengthens the robustness of the model. The results offer an accurate and economical approach for HHV estimation, which will be useful for improving the MSW management and WTE conversion procedures.

Enhancing Soil Salinity Evaluation Accuracy in Arid Regions: An Integrated Spatiotemporal Data Fusion and AI Model Approach for Arable Lands

Soil salinization is one of the primary factors contributing to land degradation in arid areas, severely restricting the sustainable development of agriculture and the economy. Satellite remote sensing is essential for real-time, large-scale soil salinity content (SSC) evaluation. However, some satellite images have low temporal resolution and are affected by weather conditions, leading to the absence of satellite images synchronized with ground observations. Additionally, some high-temporal-resolution satellite images have overly coarse spatial resolution compared to ground features. Therefore, the limitations of these spatiotemporal features may affect the accuracy of SSC evaluation. This study focuses on the arable land in the Manas River Basin, located in the arid areas of northwest China, to explore the potential of integrated spatiotemporal data fusion and deep learning algorithms for evaluating SSC. We used the flexible spatiotemporal data fusion (FSDAF) model to merge Landsat and MODIS images, obtaining satellite fused images synchronized with ground sampling times. Using support vector regression (SVR), random forest (RF), and convolutional neural network (CNN) models, we evaluated the differences in SSC evaluation results between synchronized and unsynchronized satellite images with ground sampling times. The results showed that the FSDAF model’s fused image was highly similar to the original image in spectral reflectance, with a coefficient of determination (R2) exceeding 0.8 and a root mean square error (RMSE) below 0.029. This model effectively compensates for the missing fine-resolution satellite images synchronized with ground sampling times. The optimal salinity indices for evaluating the SSC of arable land in arid areas are S3, S5, SI, SI1, SI3, SI4, and Int1. These indices show a high correlation with SSC based on both synchronized and unsynchronized satellite images with ground sampling times. SSC evaluation models based on synchronized satellite images with ground sampling times were more accurate than those based on unsynchronized images. This indicates that synchronizing satellite images with ground sampling times significantly impacts SSC evaluation accuracy. Among the three models, the CNN model demonstrates the highest predictive accuracy in SSC evaluation based on synchronized and unsynchronized satellite images with ground sampling times, indicating its significant potential in image prediction. The optimal evaluation scheme is the CNN model based on satellite image synchronized with ground sampling times, with an R2 of 0.767 and an RMSE of 1.677 g·kg−1. Therefore, we proposed a framework for integrated spatiotemporal data fusion and CNN algorithms for evaluating soil salinity, which improves the accuracy of soil salinity evaluation. The results provide a valuable reference for the real-time, rapid, and accurate evaluation of soil salinity of arable land in arid areas.

Medical image recognition based on multilayer neural network

As a common accidental injury, accurate identification of burns and scalded injuries is of great significance to the development of treatment programs and prognosis assessment. Traditional identification methods are subjective and inaccurate, this paper proposes a burns and scalds grade identification technique based on multilayer neural network. The three-degree classification standard of burns and scalds is described, and the structure and principle of multilayer neural network are introduced, including the network structure composed of input layer, hidden layer and output layer, forward propagation, back propagation and training process. The implementation steps of burns and scald grade recognition technology based on multi-layer neural network are discussed in detail, such as data acquisition, image pre-processing, feature extraction, classifier design, model training and evaluation. Through experiments, the model is tested using a dataset containing 362 burns and scalds images, and the model achieves more than 90% accuracy on the test set with high accuracy and reliability. The multi-layer neural network model is used to classify the burn and scald data, which improves the diagnostic accuracy, shortens the delay time of the disease, reduces the pressure of professional doctors, and helps patients have a preliminary understanding of the degree of burn.

A detailed analysis of game statistics of professional tennis players: An inferential and machine learning approach.

Tennis, a widely enjoyed sport, motivates athletes and coaches to optimize training for competitive success. This retrospective predictive study examines anthropometric features and statistics of 1990 tennis players in the 2022 season, using 20,040 data points retrospectively obtained from the ATP official source after the end of the season. These data were cross-verified with information from other sources before categorisation to address any discrepancies. Employing various analytical methods, the results emphasize the strategic importance of tournament participation and gameplay for financial gains and higher rankings. Prize money analysis reveals a significant disparity favoring top players. Multivariate Analysis of Variance highlights the need to consider multiple variables for understanding ATP rankings. Multinomial Logistic Regression identifies age, height, and specific service-related metrics as key determinants, with older and taller players more likely to secure top positions. Neural Network models exhibit potential in predicting ATP Rank outcomes, particularly for ATP Rank (500). Our results argue for the use of Artificial Intelligence (AI), specifically Neural Networks, in handling complex interactions and emphasize that AI is a supportive tool in decision-making, requiring careful consideration by experienced individuals. In summary, this study enhances our understanding of ATP ranking factors, providing actionable insights for coaches, players, and stakeholders in the tennis community.

Recognizing human activities using light-weight and effective machine learning methodologies

Background Human activity recognition (HAR) is increasingly important in enhancing healthcare systems by enabling accurate monitoring of individuals' movements through sensor data. This paper is motivated by the need to improve the accuracy of HAR, particularly for applications in e-health systems, where reliable activity detection can lead to better health outcomes. The study explores six prominent machine learning techniques—decision tree, random forest, linear regression, Naïve Bayes, k-nearest neighbor, and neural networks—to determine which methods can most effectively predict activities like walking, sitting, standing, laying, walking upstairs, and walking downstairs. Methods We employed these six machine learning algorithms to analyze a comprehensive dataset derived from various sensors. Each model was rigorously trained and evaluated to compare its effectiveness in recognizing human activities. The experiments aimed to identify strengths and weaknesses in each approach, with particular emphasis on advanced techniques such as random forest, convolutional neural networks (CNNs), and gated recurrent networks (GRNs). Results The experimental evaluation revealed that the random forest classifier, CNN, GRN, and neural networks delivered promising results, achieving high accuracy levels. Notably, the neural network model excelled, attaining an impressive accuracy of 98%. In contrast, the Naïve Bayes model did not meet the performance expectations set by the other algorithms. Conclusions This research effectively classifies activities such as sitting, standing, laying, walking, walking downstairs, and walking upstairs, underscoring the potential of machine learning in HAR. The findings highlight the superior performance of neural networks in enhancing activity recognition, which could lead to advanced applications in e-health systems and improve overall healthcare monitoring strategies.

A probabilistic forecast for multi-year ENSO using Bayesian convolutional neural network

Abstract A robust El Niño Southern Oscillation (ENSO) prediction is essential for monitoring the global climate, regional monsoons, and weather extremes. Despite dedicated efforts spanning decades, the precise prediction of ENSO events through numerical modeling beyond a couple of seasonal lead times remains a daunting challenge. The advent of deep learning-based approaches marks a transformative era in climate and weather prediction. However, many machine learning-based studies attempting ENSO prediction are confined to singular estimates, lacking adequate quantification of uncertainty in learned parameters and overlooking the crucial need for a nuanced understanding of ENSO prediction confidence. Here, we introduce a deep learning-based Bayesian convolutional neural network model that provides robust probabilistic predictions for ENSO with a lead time of up to 9–10 months across all seasons. The Bayesian layers within the convolutional neural network maintain the capability to predict a distribution of learned parameters. Augmented with bias correction, our model reproduces the amplitude of the Niño 3.4 index with fidelity for lead up to 9–10 months. The inherent capacity for uncertainty modeling enhances the reliability of bayesian neural networks (BNNs), making them particularly valuable in operational services. This research holds substantial socio-economic implications as it enhances our forecasting capabilities and rigorously quantifies forecast uncertainties, providing valuable insights for planning and policymaking.

Chaotic control of a simply supported beam in a multidimensional system

In this work, a control strategy based on fuzzy sliding mode control (FSMC) is applied to effectively manage the large-amplitude chaotic vibrations exhibited by a simply supported beam. The analysis considers the nonlinear beam structure, which is subjected to an external load. Hamilton’s principle is employed, and the equations of motion are derived for the studied structure. The 3rd Galerkin discretization is employed to derive the ordinary differential governing equation of the structure. A control strategy is presented to decrease the response of the obtained multidimensional system. The vibration of a one-dimensional system is compared with that of the derived multidimensional system. As shown throughout the study, a multidimensional nonlinear system of the structure must be considered for accurate dynamic estimation. By using the recurrent neural network (RNN) model, we can accurately predict chaotic motion and effectively apply control strategies to suppress chaotic motion. The efficacy and suitability of the employed control strategy have been demonstrated by controlling chaos in the beam’s multidimensional system.

Balanced Training Sets Improve Deep Learning-Based Prediction of CRISPR sgRNA Activity.

CRISPR-Cas systems have transformed the field of synthetic biology by providing a versatile method for genome editing. The efficiency of CRISPR systems is largely dependent on the sequence of the constituent sgRNA, necessitating the development of computational methods for designing active sgRNAs. While deep learning-based models have shown promise in predicting sgRNA activity, the accuracy of prediction is primarily governed by the data set used in model training. Here, we trained a convolutional neural network (CNN) model and a large language model (LLM) on balanced and imbalanced data sets generated from CRISPR-Cas12a screening data for the yeast Yarrowia lipolytica and evaluated their ability to predict high- and low-activity sgRNAs. We further tested whether prediction performance can be improved by training on imbalanced data sets augmented with synthetic sgRNAs. Lastly, we demonstrated that adding synthetic sgRNAs to inherently imbalanced CRISPR-Cas9 data sets from Y. lipolytica and Komagataella phaffii leads to improved performance in predicting sgRNA activity, thus underscoring the importance of employing balanced training sets for accurate sgRNA activity prediction.

Exploring the predictive power of artificial neural networks in linking global Islamic indices with a local Islamic index

This study aims to analyze the correlations and information flow between a local Sharia-compliant index and global Sharia-compliant indices using Artificial Neural Network (ANN) models, shedding light on the integration of international and national Sharia-compliant markets. Given recent market conditions and uncertainties at both local and global levels, the research investigates the predictive power of ANNs and examines the relationship between the Dubai Financial Market Sharia Index (DFMSI) and three well-known global Islamic indices: the Dow Jones Islamic Market World Index, the Standard and Poor’s Global Sharia Index, and the Financial Times Stock Exchange Sharia All World Index. By incorporating data from multiple global Sharia indices, the study expands data sources beyond the local market, providing a comprehensive analysis of factors influencing the DFMSI’s price. This approach reduces reliance on a single dataset and strengthens the robustness of the research findings. Additionally, the inclusion of the three global Sharia indices offers benefits such as access to global market insights, risk management, and practical applications for investors. The study demonstrates that ANNs, particularly the Nonlinear Autoregressive with External Input Neural Network (NARX), outperform classical models in accurately predicting the DFMSI. This research contributes significantly to the understanding of Sharia-compliant investments by providing a comprehensive analysis of how multiple global indices affect a local market index. It also offers valuable insights for investors and portfolio managers, suggesting that the integration of advanced machine learning models can enhance decision-making processes and improve risk management strategies.

Deep learning-assisted local resonance strategy for accurate internal damage imaging in composites

In this paper, we propose a deep neural network-assisted strategy to accurately and efficiently identify local defect resonance (LDR) modes and accurately image the internal damage in composites. A two-dimensional convolutional neural network (2D-CNN) model was constructed to identify LDR modes. The frequency-domain contour maps were used as input data, given that the LDR phenomenon exhibits discernible physical attributes in the frequency domain that are conducive to deep neural network assimilation. The obtained results demonstrate effective training outcomes and transferability, even with a limited number of samples. The LDR modes are efficiently extracted by the developed 2D-CNN model and used to obtain the accurate imaging of internal damages in composites.

Retraction Note: An improved and low-complexity neural network model for curved lane detection of autonomous driving system

Retraction Note: An improved and low-complexity neural network model for curved lane detection of autonomous driving system

IFNN: Intuitionistic Fuzzy Logic Based Neural Network Model for Time Series Forecasting

IFNN: Intuitionistic Fuzzy Logic Based Neural Network Model for Time Series Forecasting

Artificial Neural Network Model to Predict the Exportation of Traditional Products of Colombia

This article develops the design, training, and validation of a computational model to predict the exportation of traditional Colombian products using artificial neural networks. This work aims to obtain a model using a single multilayer neural network. The number of historical input data (delays), the number of layers, and the number of neurons were considered for the neural network design. In this way, an experimental design of 64 configurations of the neural network was performed. The main arduousness addressed in this work is the significant difference (in tons) in the values of the considered products. The results show the effect that occurs due to the different range values, and one of the proposals made allows this limitation to be handled appropriately. In summary, this work seeks to provide essential information for formulating a model for efficient and practical application.

The role of motor cortex in motor sequence execution depends on demands for flexibility.

The role of the motor cortex in executing motor sequences is widely debated, with studies supporting disparate views. Here we probe the degree to which the motor cortex's engagement depends on task demands, specifically whether its role differs for highly practiced, or 'automatic', sequences versus flexible sequences informed by external cues. To test this, we trained rats to generate three-element motor sequences either by overtraining them on a single sequence or by having them follow instructive visual cues. Lesioning motor cortex showed that it is necessary for flexible cue-driven motor sequences but dispensable for single automatic behaviors trained in isolation. However, when an automatic motor sequence was practiced alongside the flexible task, it became motor cortex dependent, suggesting that an automatic motor sequence fails to consolidate subcortically when the same sequence is produced also in a flexible context. A simple neural network model recapitulated these results and offered a circuit-level explanation. Our results critically delineate the role of the motor cortex in motor sequence execution, describing the conditions under which it is engaged and the functions it fulfills, thus reconciling seemingly conflicting views about motor cortex's role in motor sequence generation.

Sex-bias metabolism of fetal organs, and their relationship to the regulation of fetal brain-placental axis.

The placenta plays influential role in the fetal development of mammals. But how the metabolic need of the fetal organs is related to that of the placenta, and whether this relationship is influenced by the sex of the fetus remain poorly understood. This study used pigs to investigate metabolomic signatures of male and female fetal organs, and determine the relevance of gene expression of the placenta and brain to the metabolism of peripheral organs. Untargeted metabolomics analysis was performed with the day-45 placenta, kidney, heart, liver, lung and brain of male and female pig fetuses to model sex differences in themetabolism of the peripheral organs relative to that of the brain and placenta. Transcriptomic analysis was performed to investigate the expression of metabolic genes in the placenta and fetal brain of both sexes. The results of this study show that the fetoplacental metabolic regulation was not only influenced by the fetal sex but also dependent on the metabolic requirement of theindividual organs of the fetus. Neural network modeling of metabolomics data revealed differential relationship of the metabolic changes of the peripheral organs with the placenta and fetal brain between males and females. RNA sequencing further showed that genes associated with themetabolism of the peripheral organs were differentially expressed in the placenta and fetal brain. The findings of this study suggest a regulatory role of the fetal brain and placenta axis in the sex-bias metabolism of the peripheral organs.

Accurate prediction of protein–ligand interactions by combining physical energy functions and graph-neural networks

We introduce an advanced model for predicting protein–ligand interactions. Our approach combines the strengths of graph neural networks with physics-based scoring methods. Existing structure-based machine-learning models for protein–ligand binding prediction often fall short in practical virtual screening scenarios, hindered by the intricacies of binding poses, the chemical diversity of drug-like molecules, and the scarcity of crystallographic data for protein–ligand complexes. To overcome the limitations of existing machine learning-based prediction models, we propose a novel approach that fuses three independent neural network models. One classification model is designed to perform binary prediction of a given protein–ligand complex pose. The other two regression models are trained to predict the binding affinity and root-mean-square deviation of a ligand conformation from an input complex structure. We trained the model to account for both deviations in experimental and predicted binding affinities and pose prediction uncertainties. By effectively integrating the outputs of the triplet neural networks with a physics-based scoring function, our model showed a significantly improved performance in hit identification. The benchmark results with three independent decoy sets demonstrate that our model outperformed existing models in forward screening. Our model achieved top 1% enrichment factors of 32.7 and 23.1 with the CASF2016 and DUD-E benchmark sets, respectively. The benchmark results using the LIT-PCBA set further confirmed its higher average enrichment factors, emphasizing the model’s efficiency and generalizability. The model’s efficiency was further validated by identifying 23 active compounds from 63 candidates in experimental screening for autotaxin inhibitors, demonstrating its practical applicability in hit discovery.Scientific contributionOur work introduces a novel training strategy for a protein–ligand binding affinity prediction model by integrating the outputs of three independent sub-models and utilizing expertly crafted decoy sets. The model showcases exceptional performance across multiple benchmarks. The high enrichment factors in the LIT-PCBA benchmark demonstrate its potential to accelerate hit discovery.

Application and Empirical Analysis of Fuzzy Neural Networks in Mining Social Media Users’ Behavioral Characteristics and Formulating Accurate Online Marketing Strategies

In the current digital social environment, social media platforms have become an important position for user behavior insights and precision marketing. User behavioral data on social media contain rich information, but they are often fuzzy, uncertain and highly complex. Fuzzy neural network (FNN), as an advanced model combining fuzzy logic and neural network theory, provides a powerful tool for processing and analyzing social media user behavioral features. This study is dedicated to exploring the application of fuzzy neural networks in social media user behavior analysis and their key role in the design of accurate online marketing strategies. We construct and optimize a fuzzy neural network model by meticulously classifying and quantifying user behavioral features, including behavioral frequency features, content topic features, social interaction features, and time series features, as well as applying fuzzy set theory to deal with fuzzy features such as emotional states. Through empirical analysis, we will show how fuzzy neural networks can reveal the intrinsic laws behind user behaviors, and how these insights can be used to design and implement precise online marketing strategies to improve advertising effectiveness, user engagement, and brand loyalty.