Neural Network Method Research Articles

A high-resolution method for direction of arrival estimation based on an improved self-attention module.

The high-resolution direction of arrival (DOA) estimation is a prominent research issue in underwater acoustics. The existing high-resolution methods include subspace methods and sparse representation methods. However, the performance of subspace methods suffers from low signal-to-noise ratio (SNR) and limited snapshots conditions, and the computational complexity of sparse representation methods is too high. The neural network methods are emerging high-resolution methods. However, insufficient support for big data is frequently observed in underwater acoustics, and conventional network structures present challenges in further enhancing performance. To address the aforementioned problems, we propose a neural network method based on an improved self-attention module to achieve high accuracy and robust DOA estimation. First, we design a multi-head self-attention module with large-scale convolutional kernels and residual structures to improve the estimated accuracy. Second, we propose an improved input feature to enhance the robustness to non-uniform noise and unequal-intensity targets. The simulations demonstrate that the proposed method exhibits superior angle resolution compared to sparse representation methods under the same simulation conditions. The proposed method demonstrates exceptional accuracy and robustness in DOA estimation under challenging conditions of low SNR, limited snapshots, and unequal-intensity targets. The experimental results further prove the effectiveness of the proposed method.

Prediction of Rheological Properties of Flour From Physicochemical Properties Using Multiple Regression Techniques and Artificial Neuronal Networks

ABSTRACTThis study has two main objectives: (i) to determine the physicochemical and rheological properties of different flours and (ii) to estimate the alveograph parameters obtained as a result of experimental studies. In this context, physicochemical (protein, ash, falling number, wet gluten, gluten index, Zeleny, and delayed sedimentation) and alveograph parameters (P, L, G, W, P/L, and IE) of 150 different bread and pastry flours were determined. Multiple regression analysis (MRA) and artificial neural network (ANN) methods were then used to predict alveograph results from this experimentally obtained data set. Root mean square error (RMSE), mean absolute error (MAE), Nash‐Sutcliffe (NSEC), and relative error (RE) performance statistics were used to evaluate the CS prediction capabilities of the methods. It was found that the flours were in the range of 11.01%–13.82% protein, 325–403 s falling number, and 30–61 mL Zeleny and delayed sedimentation values. The ANN method showed better predictive performance than the regression‐based method. W was the best estimated parameter in the ANN model. This was followed by G, L, Ie, P/L, and P values. Considering the RMSE value of the W parameter, it was observed that the ANN method provided an improvement of 5.16, 1.76, and 2.15 times compared to the regression method for the training, validation, and test sets, respectively.

Estimating water quality parameters of freshwater aquaculture ponds using UAV-based multispectral images

UAV imaging technology has become one of the means to quickly monitor water quality parameters in freshwater aquaculture ponds. The change of sunlight during a long flight affects the quality of UAV images, which will reduce the accuracy of monitoring water quality. This study aims to propose a method to correct spectral variation during UAV imaging and apply it to detect dissolved organic matter (DOM) concentration and dissolved oxygen (DO) content in freshwater aquaculture ponds. Firstly, a spectral correction method was used to transform UAV-based multispectral images. The spectral data before and after correction was extracted. Secondly, 18 spectral indices before and after correction were constructed. The optimal combination of indices was identified using correlation analysis algorithm. The estimation models of water quality parameters were then constructed and compared using the Random Forest (RF), Support Vector Regression (SVR), and BP neural network (BP) methods. The results showed that the accuracy of estimating DOM concentration using corrected spectral indices was significantly improved compared to pre-correction models, with the highest improvement of 38 % (SVR), the lowest of 23 % (BP), and an average improvement of 31 %. The RF model performed best, achieving R² = 0.81, RMSE = 3.34 mg/L, and MAE = 2.17 mg/L. For DO content estimation, the accuracy of models using corrected spectral indices was also improved significantly, with the highest improvement of 97 % (RF), the lowest of 39 % (SVR), and an average improvement rate of 67 %. The Random Forest model was again optimal, with R² = 0.69, RMSE = 1.97 mg/L, and MAE = 1.47 mg/L. This study indicates that the proposed spectral correction method helps to map the concentration of DOM and DO in freshwater aquaculture ponds with high accuracy using UAV-based multispectral images.

Graph Neural Network-Based Node Deployment for Throughput Enhancement.

The recent rapid growth in mobile data traffic entails a pressing demand for improving the throughput of the underlying wireless communication networks. Network node deployment has been considered as an effective approach for throughput enhancement which, however, often leads to highly nontrivial nonconvex optimizations. Although convex-approximation-based solutions are considered in the literature, their approximation to the actual throughput may be loose and sometimes lead to unsatisfactory performance. With this consideration, in this article, we propose a novel graph neural network (GNN) method for the network node deployment problem. Specifically, we fit a GNN to the network throughput and use the gradients of this GNN to iteratively update the locations of the network nodes. Besides, we show that an expressive GNN has the capacity to approximate both the function value and the gradients of a multivariate permutation-invariant function, as a theoretic support to the proposed method. To further improve the throughput, we also study a hybrid node deployment method based on this approach. To train the desired GNN, we adopt a policy gradient algorithm to create datasets containing good training samples. Numerical experiments show that the proposed methods produce competitive results compared with the baselines.

Batik Pattern Classification Using Machine Learning Approaches

Batik is one of Malaysia traditional textile art form that is well known. By using Artificial Neural Network (ANN), k-Nearest Neighbors (k-NN) and Decision Tree methods, this study aims to classify Kelantan batik designs according to flora, fauna and geometry motifs. 133 images of the three categories were collected from social media and underwent pre-processing techniques. Image augmentation was done to enhance the diversity and quality of available training data for machine learning models. Digital transformation on the images based on colour features was developed to classify the three types of batik motifs. Image embedding was employed which returned a vector representation of each image in a data table in Orange software. The data divided into training and testing dataset, with a ratio of 8:2. The performance of each machine learning techniques were compared. The findings showed that ANN produced an excellent performance as indicated by classification accuracy (CA) of 87.9% for original images and 82.2% using Luminance Gradient image transformation technique. ANN also returns the highest AUC score indicating it is the best in distinguishing the images motif. Results from confusion matrix showed that ANN have the least misclassification for batik classification. Based on the result, it signifies that ANN performs the best classification among the three approaches.

Prediction of polarization curves of PEMFC membrane electrode assembly using artificial intelligence technics

Proton exchange membrane fuel cells (PEMFCs) are used commercially in automobiles, buses, uninterruptible power supplies, and combined heat power systems, holding a significant place in the fuel cell market. Fuel cell performance is characterized by polarization curves in design and manufacturing processes. This study predicts a PEMFC’s polarization curves using comparative artificial intelligence (AI) models trained and tested under different operational conditions. The AI model inputs are cell temperature, humidity, anode-cathode flow, and membrane resistance. The outputs are cell voltage and current density. The model outputs are compared with experimental values for 50°C, 100% humidity using MATLAB software. The average Root Mean Square Error (RMSE) for the ANFIS prediction is 0.056112, while for the ANN prediction it is 0.011919. These results indicate that the Artificial Neural Network (ANN) method outperforms the Adaptive Neuro Fuzzy Inference System (ANFIS) in predicting the behavior of the PEMFC’s Membrane Electrode Assembly (MEA). The models showed promising results with high accuracy.

Data-driven prediction of vortex solitons and multipole solitons in whispering gallery mode microresonator

Deep learning incorporating physics knowledge has become a powerful tool for studying the dynamic behavior of high-dimensional nonlinear systems. In this paper, the two-stage mini-batch resampling of adaptive physics-informed neural network (TMA-PINN) method is proposed to solve the (2 + 1)-dimensional variable-coefficient Lugiato-Lefever equation (vLLE). The vortex soliton in the WGM microresonator with different external excitation is investigated by TMA-PINN. It is found that external excitation can cause the rotation of vortex solitons. In addition, the effect of topological charge and external excitation on the dynamical characteristics of spatial solitons including vortex solitons and multipole solitons are investigated. The results show that the final shape of the rotation of vortex solitons and the number of azimuth lobes of multipole solitons are controlled by topological charges. Compared with classical PINN, TMA-PINN can better handle the gradient balance of various loss terms in (2 + 1)-dimensional vLLE to reconstruct the dynamic behavior of WGM microresonator solitons, having potential applications in other nonlinear systems.

The application of explainable artificial intelligence methods to models for automatic creativity assessment.

The study is devoted to comparing various models based on Artificial Intelligence to determine the level of creativity based on drawings performed using the Urban test, as well as analyzing the results of applying explainable artificial intelligence methods to a trained model to identify the most relevant features in drawings that influence the model's prediction. The dataset is represented by a set of 1,823 scanned forms of drawings of participants performed according to the Urban test. The test results of each participant were assessed by an expert. Preprocessed images were used for fine-tuning pre-trained models such as MobileNet, ResNet18, AlexNet, DenseNet, ResNext, EfficientNet, ViT with additional linear layers to predict the participant's score. Visualization of the areas that are of greatest importance from the point of view of the model was carried out using the Gradient-weighted Class Activation Mapping (Grad-CAM) method. Trained models based on MobileNet showed the highest prediction accuracy rate of 76%. The results of the application of explainable artificial intelligence demonstrated areas of interest that correlated with the criteria for expert assessment according to the Urban test. Analysis of erroneous predictions of the model in terms of interpretation of areas of interest made it possible to clarify the features of the drawing on which the model relies, contrary to the expert. The study demonstrated the possibility of using neural network methods for automated diagnosis of the level of creativity according to the Urban test based on the respondents' drawings. The application of explainable artificial intelligence methods to the trained model demonstrated the compliance of the identified activation zones with the rules of expert assessment according to the Urban test.

Research on Graph Multi-Attention Neural Network for Power System Transient Stability Assessment

Abstract Diagnosing the stability of power grids based on artificial intelligence technology is a research trend. The existing artificial intelligence stability analysis methods rely on a large number of fault case data, while the graph neural network method ignores the correlation characteristics of nodes themselves and the correlation of long-distance nodes. In order to solve the problems, the graph multi-attention neural network (GMANN) was proposed. The self-attention, which characterizes the correlation between different state quantities of a single node, is proposed, firstly. Then, long-distance association attention, which represents the correlation of distant nodes in the power grid, was proposed. The long-distance correlation attention and the adjacent correlation attention in graph attention network are fused to form a global attention that reflects the global importance of the power grid. The channel attention that characterizes the importance of different pooling methods of graph convolutional network is extracted and used to obtain the importance of different convolution operations. Finally, based on the multi-source attention fusion strategy, global attention and channel attention are embedded in the graph attention neural network to form a multi-level evaluation model to achieve power grid stability evaluation efficiently guided by multiple attentions. The proposed GMANN is verified based on simulated fault cases obtained from the 10-machine 39-node system in New England. The results show that the accuracy of the GMANN can reach 97.34%, which is better than other methods. And the missed judgment rate of important indicators is significantly better than other methods.

An Adaptive X‐Ray Dynamic Image Estimation Method Based on OMNI Solar Wind Parameters and SXI Simulated Observations

AbstractObservations of the overall interactions between solar wind and the Earth's magnetosphere are crucial for space weather monitoring. Upcoming missions like the Solar Wind Magnetosphere Ionosphere Link Explorer (SMILE) and the Lunar Environment heliosphere X‐ray Imager (LEXI) aim to make comprehensive global imaging of Earth's magnetosphere using soft X‐ray imager (SXI) in order to understand its dynamic response to solar wind impact. Short‐duration X‐ray images have a low signal‐to‐noise ratio (SNR), limited by cosmic background and Poisson noise. Longer integration times provide better SNR of magnetospheric structures but fail to capture the short‐term dynamics during the integration. Our study introduces a neural network method which is able to estimate the short‐term dynamics during a long integration, driven by OMNI solar wind data and simulated soft X‐ray images. Specifically, an adaptive X‐ray image estimator and a spatio‐temporal discriminator are used. It leverages X‐ray models like Magnetohydrodynamic (MHD) and Jorgensen & Sun model, driven by OMNI data to provide high‐temporal‐resolution prior information on magnetosphere motion, with SXI observation images acting as a posterior constraint on the magnetosphere's state. Experimental validation demonstrates apparent improvements in Peak signal‐to‐noise ratio (PSNR) and Structural Similarity (SSIM) compared to traditional linear and optical flow interpolation methods. The method's flexibility, considering input‐output consistency, enables easy extension to any interval (>3 min), meeting diverse application needs. In conclusion, our study presents a new approach to soft X‐ray image estimation based on neural networks, providing insights into magnetospheric dynamics as observed in soft X‐rays.

Research on porosity prediction method for petroleum reservoirs based on improved gene expression algorithm

Abstract Porosity, an essential parameter of reservoir properties, plays a crucial role in reservoir evaluation. Indirect prediction of reservoir porosity using well-logging data is a fundamental task in assessing hydrocarbon reserves. Multivariate stepwise regression and artificial neural network methods are currently typical prediction approaches. However, these methods suffer from drawbacks such as high workload, extensive training sample requirements, and high computational costs. Genetic Expression Programming (GEP), a novel genetic algorithm, exhibits remarkable function discovery capabilities, high efficiency, and the ability to function without requiring large training samples. This paper proposes a method that utilizes GEP to mine a porosity calculation model from well-logging sample data and subsequently compute the porosity. The effectiveness and efficiency of this method are validated through actual well-logging data.

Automatic sign language translation: a review of neural network methods for recognition and synthesis of spoken and signed language

Automatic sign language translation: a review of neural network methods for recognition and synthesis of spoken and signed language

Cognitive diagnostic assessment: A Q-matrix constraint-based neural network method.

Cognitive diagnosis is a crucial element of intelligent education that aims to assess the proficiency of specific skills or traits in students at a refined level and provide insights into their strengths and weaknesses for personalized learning. Researchers have developed numerous cognitive diagnostic models. However, previous studies indicate that diagnostic accuracy can be significantly influenced by the appropriateness of the model and the sample size. Thus, designing a general model that can adapt to different assumptions and sample sizes remains a considerable challenge. Artificial neural networks have been proposed as a promising approach in some studies. In this paper, we propose a cognitive diagnosis model of a neural network constrained by a Q-matrix and named QNN. Specifically, we employ the Q-matrix to determine the connections between neurons and the width and depth of the neural network. Moreover, to reduce the human effort in the training algorithm, we designed a self-organizing map-based cognitive diagnosis training framework called SOM-NN, which enables the QNN to be trained unsupervised. Extensive experimental results on simulated and real datasets demonstrate that our approaches are effective in both accuracy and interpretability. Notably, under unsupervised conditions, our approach has significant advantages on small sample datasets with high levels of guessing and slipping, especially on the pattern-wise agreement rates. This work bridges the gap between psychometrics and machine learning and provides a realistic and implementable reference solution for classroom instructional assessment and the cold start of personalized and adaptive assessment systems.

The Eye and Nose Identification Chip Controller-Based on Robot Vision Using Weightless Neural Network Method

Increasingly advanced image analysis in computer vision, allowing computers to interpret, identify, and analyze pictures with accuracy comparable to humans. The availability of data sources in decimal, hexadecimal, or binary forms enables researchers to take the initiative in applying their study findings. Decimal formats are typically used on traditional computers like desktops and minicomputers, whereas hexadecimal and binary formats were utilized on single-chip controllers. Weightless Neural Network is a method that can be implemented in a single chip controller. The aim of this research is to develop a facial recognition system, for eye and mouth identification, that works in a single chip controller or also called a microcontroller. The suggested method is a Weightless Neural Network with Immediate Scan approach for processing and identifying eye and nose patterns. The data will be handled in many memory locations that are specifically designed to handle massive volumes of data. The data is made up of primary face data sheets and face input data. The data sets utilized are (x,y) pixels, and frame sizes range from 90x90 pixels to 110x110 pixels. Each face shot will be processed by selecting the region of the eyes and nose and saving it as an image file. The eye and nose will identify the face frame. Next, the photos will be converted to binary format. A magazine matrix will be used to transmit binary data from a minicomputer to a microcontroller via serial connection. Based on a known pattern, the resultant similarity accuracy is 83,08% for the eye and 84,09% for the sternum. In contrast, the similarity percentage for an eye ranges from 70% to 85% for an undefined pattern.

Using artificial intelligence based imaging to predict lymph node metastasis in non-small cell lung cancer: a systematic review and meta-analysis.

Lung cancer, especially non-small cell lung cancer (NSCLC), is one of the most-deadly malignancies worldwide. Lung cancer has a worse 5-year survival rate than many primary malignancies. Thus, the early detection and prognosis prediction of lung cancer are crucial. The early detection and prognosis prediction of lung cancer have improved with the widespread use of artificial intelligence (AI) technologies. This meta-analysis examined the accuracy and efficacy of AI-based models in predicting lymph node metastasis (LNM) in NSCLC patients using imaging data. Our findings could help clinicians predict patient prognosis and select alternative therapies. We searched the PubMed, Web of Science, Cochrane Library, and Embase databases for relevant articles published up to January 31, 2024. Two reviewers individually evaluated all the retrieved articles to assess their eligibility for inclusion in the meta-analysis. The systematic assessment and meta-analysis comprised articles that satisfied the inclusion criteria (e.g., randomized or non-randomized trials, and observational studies) and exclusion criteria (e.g., articles not published in English), and provided data for the quantitative synthesis. The quality of the included articles was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). The pooled sensitivity, specificity, and area under the curve (AUC) were used to evaluate the ability of AI-based imaging models to predict LNM in NSCLC patients. Sources of heterogeneity were investigated using meta-regression. Covariates, including country, sample size, imaging modality, model validation technique, and model algorithm, were examined in the subgroup analysis. The final meta-analysis comprised 11 retrospective studies of 6,088 NSCLC patients, of whom 1,483 had LNM. The pooled sensitivity, specificity, and AUC of the AI-based imaging model for predicting LNM in NSCLC patients were 0.87 [95% confidence interval (CI): 0.80-0.91], 0.85 (95% CI: 0.78-0.89), and 0.92 (95% CI: 0.90-0.94). Based on the QUADAS-2 results, a risk of bias was detected in the patient selection and diagnostic tests of the included articles. However, the quality of the included articles was generally acceptable. The pooled sensitivity and specificity were heterogeneous (I2>75%). The meta-regression and subgroup analyses showed that imaging modality [computed tomography (CT) or positron emission tomography (PET)/CT], and the neural network method model design significantly affected heterogeneity of this study. Models employing sample size data from a single center and the least absolute shrinkage and selection operator (LASSO) method had greater sensitivity than other techniques. Using the Deek' s funnel plot, no publishing bias was found. The results of the sensitivity analysis showed that deleting each article one by one did not change the findings. Imaging data models based on AI algorithms have good diagnostic accuracy in predicting LNM in patients with NSCLC and could be applied in clinical settings.

Long term demand forecasting in Jakarta distribution grid system using fuzzy logic and artificial neural network method

Abstract In order to attain equilibrium between energy supply and demand, reliance on conventional methods for precise long-term electricity demand forecasting is no longer viable. The utilization of artificial intelligence, such as fuzzy logic and artificial neural network (ANN) models, emerges as a prospective solution in the current dynamic scenario. This research explores long-term electricity demand forecasting within the Jakarta distribution grid system, employing various fuzzy logic and ANN approaches including Sugeno, Mamdani, Bayesian Regularization, and the Levenberg algorithm. The analysis incorporates time series data spanning 2016 to 2019, encompassing electricity load demand, economic factors, and demographic variables, processed using MATLAB. The outcomes of the four forecasting methods reveal an average error range of 2 to 3%. The findings indicate that employing fuzzy logic and ANN methods for long-term electricity demand forecasting can yield a forecast error of less than 3%. The study recommends future research enhancements through the inclusion of additional time series data and a more refined system.

Construction of data base containing flow field information under different blade placement of pumping station in digital twin

Abstract The data base in digital twin technology includes various data such as the structure, performance, and operating status of the physical object. And the data base is the key point for the construction of the digital twin system. However, the data bases of different digital twin systems usually contain different information. In this paper, the flow state of the pumping station under different angles of four blades is selected as the research object. The research methods in this paper mainly include Latin hypercube sampling, numerical simulation and neural network prediction. The Latin hypercube sampling is used to select the typical Angle difference model. The numerical simulation is used to obtain flow field information. The neural network prediction method is used to construct a complete data base. The study incorporates an actual large-scale mixed-flow pump station to head, efficiency, and shaft power as the prediction targets. It utilizes the different angle difference data of ten sets of four blades as the training set, forty sets of remaining samples as the experiment set, and employs the backpropagation neural network method for constructing the prediction network. By changing the experiment set and test set, the method can efficiently complete the construction of data base including actual test and numerical simulation, which provides a solid foundation for the construction of digital twin platform.

Comparative Analysis of the Methods of Planning and Coordinating of Manipulator Robot Movement

This paper presents a comparative analysis of two methods for planning and coordinating the movement of robot manipulators in dynamic environments: a neural network-based approach for solving dynamic production scenarios and the rapidly exploring random trees algorithm. The study aims to enhance the trajectory planning of robot manipulators by leveraging the strengths of intelligent systems. The neural network method is designed to perceive the environment, generate accurate control commands, and adapt to changing conditions in real-time. The paper the processes involved in environmental analysis, collision avoidance, and control signal generation for actuators, with an emphasis on the neural network architecture tailored for these tasks. The results demonstrate that the neural network approach offers significant improvements in adaptability and efficiency, providing a robust solution for optimizing automated processes in dynamic production environments.

Neural Network Optimization Using Hybrid Adaptive Mutation Particle Swarm Optimization and Levenberg-Marquardt in Cases of Cardiovascular Disease

Abstract. Cardiovascular disease is a condition generally characterized by the narrowing or blockage of blood vessels, which can lead to heart attacks, chest pain, or strokes. It is the leading cause of death worldwide, accounting for approximately 31% or 17.9 million deaths each year globally. Deaths caused by cardiovascular disease are projected to continue increasing until 2030, with the number of patients reaching 23.3 million. As cases of death due to cardiovascular disease become more prevalent, early detection is crucial to reduce mortality rates. Purpose: Many previous researchers have conducted studies on predicting cardiovascular disease using neural network methods. This study extends these methods by incorporating feature selection and optimization with Hybrid AMPSO-LMA. The research is designed to explore the implementation and predictive outcomes of Hybrid AMPSO-LMA in optimizing MLP for cases of cardiovascular disease. Methods/Study design/approach: The first step in conducting this research is to download the Heart Disease Dataset from Kaggle.com. The dataset is processed through preprocessing by removing duplicates and transforming the data. Then, data mining processes are carried out using the MLP algorithm optimized with Hybrid AMPSO-LMA to obtain results and conclusions. This system is designed using the Python programming language and utilizes Flask for website access in HTML. Result/Findings: The research results demonstrate that the method employed by the author successfully improves the accuracy of predicting cardiovascular disease. Predicting cardiovascular disease using the MLP algorithm yields an accuracy of 86.1%, and after optimization with Hybrid AMPSO-LMA, the accuracy increases to 86.88%. Novelty/Originality/Value: This effort will contribute to the development of a more reliable and effective cardiovascular disease prediction system, with the goal of early identification of individuals exhibiting symptoms of cardiovascular disease.

Comparative Analysis of Congestion Management Methods with Integrated Renewable Energy Generation

Inclusion of renewable energy in power grid at micro and macro level has imposed numerous challenges in the recent years. Occurrence and managing congestion in the power transmission line due to unpredictable and stochastic nature of Renewable Energy Source (RES) integration has become a challenging task to the grid operators. Transmission lines operate at bottlenecks during a congestion episode adding to the extra congestion cost and risk in grid stability which becomes burden to the generation as well as end users. Different methodologies are applied to detect and manage the congestion to eliminate the congestion cost factor and maintain grid stability. The presented analysis compares conventional methodology Linear Sensitivity Factors (LSF) and Heuristic methodology Particle Swarm Optimization (PSO) and Artificial Neural Network (ANN) methods for congestion management in power transmission lines with integrated RES (wind and solar) system. For comparative analysis, a modified standard IEEE 30 Bus system is chosen which is integrated with real time RES generation. Optimal locations of RES generation with minimized congestion cost and percentage of RES curtailment are chosen as objective function for comparison of the methodologies.