Application Of Neural Networks Research Articles

Borich 요구도와 The Locus for Focus model을 활용한 대학생의 챗GPT 현 수준 및 중요도 분석

Objectives The purpose of this study is to analyze the perception level of university students regarding ChatGPT using the Borich Needs and The Locus for Focus model. Methods For this purpose, a total of 199 undergraduate students from University A in the metropolitan area were selected as participants, and the research was conducted using SPSS 25.0 and Excel software programs. Statistical significance was analyzed using t-tests to examine the differences between the current level and im-portance in IPA analysis.Borich'sNeeds and The Locus for Focus Model were examined in a 2x2 matrix, divided into four quadrants. Results The key findings of this study are as follows: First, in the IPA analysis, the reinforcement and maintenance area(HH) revealed 2 items related to understanding ChatGPT, 5items related to ChatGPT principles and applica-tions, and 1 item related to data and machine learning. The concentration management area(HL) included 1 item related to ChatGPT principles and applications, and 3 items related to data and machine learning. The low priority area(LL) consisted of 1 item related to understanding ChatGPT, 2 items related to ChatGPT principles and applica-tions, and 4 items related to social impact. The excessive area(LH) was characterized bybiaseddata in the social impact category. Second, it was found that the differences between importance and current level were higher in terms of importance for all items, except for those related to data bias. This difference was statistically significant. The priority order according to Borich's needs includes 'structuredand unstructured data', 'sensorsand perception', 'computer vision', 'concepts of AI agents' and 'conceptsand application learning of machines'. Third, The Locus for Focus model analysis revealed that the HH area consisted of 9 items, including 'speech recognition and language understanding', 'problem solving and exploration', 'representation and deduction of information', 'concepts and ap-plication learning of machines', 'concepts and application of artificial neural networks', 'data attributes', 'structured and unstructured data', 'classification models', and 'machine learning model implementation'. Fourth, a total of 6 items, including 'speech recognition and language understanding', 'representation and deduction of information', 'concepts and application learning of machines', 'concepts and application of artificial neural networks', 'structured and unstructured data', and 'classification models' were consistently rated as high priority and demanded the high-est attention. Conclusions The findings of this study indicate the need to explore ways to apply ChatGPT in education. Furthermore, it proposes a long-term education plan to enhance awareness of the social impact of ChatGPT and provide practical strategies for learning and applying it.

Artificial neural network, machine learning modelling of compressive strength of recycled coarse aggregate based self-compacting concrete.

This research study aims to understand the application of Artificial Neural Networks (ANNs) to forecast the Self-Compacting Recycled Coarse Aggregate Concrete (SCRCAC) compressive strength. From different literature, 602 available data sets from SCRCAC mix designs are collected, and the data are rearranged, reconstructed, trained and tested for the ANN model development. The models were established using seven input variables: the mass of cementitious content, water, natural coarse aggregate content, natural fine aggregate content, recycled coarse aggregate content, chemical admixture and mineral admixture used in the SCRCAC mix designs. Two normalization techniques are used for data normalization to visualize the data distribution. For each normalization technique, three transfer functions are used for modelling. In total, six different types of models were run in MATLAB and used to estimate the 28th day SCRCAC compressive strength. Normalization technique 2 performs better than 1 and TANSING is the best transfer function. The best k-fold cross-validation fold is k = 7. The coefficient of determination for predicted and actual compressive strength is 0.78 for training and 0.86 for testing. The impact of the number of neurons and layers on the model was performed. Inputs from standards are used to forecast the 28th day compressive strength. Apart from ANN, Machine Learning (ML) techniques like random forest, extra trees, extreme boosting and light gradient boosting techniques are adopted to predict the 28th day compressive strength of SCRCAC. Compared to ML, ANN prediction shows better results in terms of sensitive analysis. The study also extended to determine 28th day compressive strength from experimental work and compared it with 28th day compressive strength from ANN best model. Standard and ANN mix designs have similar fresh and hardened properties. The average compressive strength from ANN model and experimental results are 39.067 and 38.36 MPa, respectively with correlation coefficient is 1. It appears that ANN can validly predict the compressive strength of concrete.

Deep learning in oral surgery for third molar extraction: empirical evidence and original model

Preemptive analgesia is an analgesic intervention to influence postoperative pain sensation. Control of postoperative pain is a major challenge for any surgeon. Adequate control of postoperative pain continues to be a challenge for modern medicine. The advent of artificial intelligence (AI) in all spheres of life, including medicine, has created the technical ability to process a variety of types and characteristics of data related to many diseases. The application of artificial neural networks in medical science has made it possible to obtain an independent, objective assessment as a consequence of the application of preemptive analgesia. The data analysis by our original model, compared with the routinely used statistical methods, show the presence of a tendency for a positive effect of preemptive analgesia. In order to obtain an efficient self-learning neural network, it is necessary to use large arrays of properly selected data that fulfill the role of input parameters for the neural network. The results obtained from the original model used are comparable to the traditionally used statistical methods. This model objectifies to a certain extent the preemptive analgesia in the surgery of third mandibular molars.

Machine Learning Approaches for ADHD Detection

This report explores the application of deep learning convolutional neural networks (CNNs) for analyzing brain MRI scans to assist in the diagnosis of Attention Deficit Hyperactivity Disorder (ADHD) syndrome. ADHD is a neuro developmental disorder that affects millions of individuals worldwide, characterized by difficulties in attention, hyperactivity, and impulsivity. Traditional methods of diagnosis rely on subjective assessments and behavioral observations, leading to inaccuracies and delays in treatment. Leveraging the power of deep learning CNNs for MRI analysis offers the potential for more objective and efficient diagnosis, facilitating timely intervention and personalized treatment strategies

Scalable Binary Neural Network Applications in Oblivious Inference

Binary neural network (BNN) delivers increased compute intensity and reduces memory/data requirements for computation. Scalable BNN enables inference in a limited time due to different constraints. This paper explores the application of Scalable BNN in oblivious inference, a service provided by a server to mistrusting clients. Using this service, a client can obtain the inference result on his/her data by a trained model held by the server without disclosing the data or learning the model parameters. Two contributions of this paper are: (1) we devise lightweight cryptographic protocols explicitly designed to exploit the unique characteristics of BNNs. (2) we present an advanced dynamic exploration of the runtime-accuracy tradeoff of scalable BNNs in a single-shot training process. While previous works trained multiple BNNs with different computational complexities (which is cumbersome due to the slow convergence of BNNs), we train a single BNN that can perform inference under various computational budgets. Compared to CryptFlow2, the state-of-the-art technique in the oblivious inference of non-binary DNNs, our approach reaches 3× faster inference while keeping the same accuracy. Compared to XONN, the state-of-the-art technique in the oblivious inference of binary networks, we achieve 2× to 12× faster inference while obtaining higher accuracy.

Some Conditions and Perturbation Theorem of Irregular Wavelet/Gabor Frames in Sobolev Space

Due to its potential applications in image restoration and deep convolutional neural networks, the study of irregular frames has interested some researchers. This paper addresses irregular wavelet systems (IWSs) and irregular Gabor systems (IGSs) in Sobolev space HsR. We obtain the sufficient and necessary conditions for IWS and IGS to be frames. By applying these conditions, we also derive the characterizations of IWS and IGS to be frames. Finally, we discuss the perturbation theorem of irregular wavelet frames (IWFs) and irregular Gabor frames (IGFs). We also provided some examples to support our results.

Knowledge mapping of graph neural networks for drug discovery: a bibliometric and visualized analysis

IntroductionIn recent years, graph neural network has been extensively applied to drug discovery research. Although researchers have made significant progress in this field, there is less research on bibliometrics. The purpose of this study is to conduct a comprehensive bibliometric analysis of graph neural network applications in drug discovery in order to identify current research hotspots and trends, as well as serve as a reference for future research.MethodsPublications from 2017 to 2023 about the application of graph neural network in drug discovery were collected from the Web of Science Core Collection. Bibliometrix, VOSviewer, and Citespace were mainly used for bibliometric studies.Results and DiscussionIn this paper, a total of 652 papers from 48 countries/regions were included. Research interest in this field is continuously increasing. China and the United States have a significant advantage in terms of funding, the number of publications, and collaborations with other institutions and countries. Although some cooperation networks have been formed in this field, extensive worldwide cooperation still needs to be strengthened. The results of the keyword analysis clarified that graph neural network has primarily been applied to drug-target interaction, drug repurposing, and drug-drug interaction, while graph convolutional neural network and its related optimization methods are currently the core algorithms in this field. Data availability and ethical supervision, balancing computing resources, and developing novel graph neural network models with better interpretability are the key technical issues currently faced. This paper analyzes the current state, hot spots, and trends of graph neural network applications in drug discovery through bibliometric approaches, as well as the current issues and challenges in this field. These findings provide researchers with valuable insights on the current status and future directions of this field.

The application of artificial neural networks to forecast financial time series

Abstract The amount of information that is produced on a daily basis in the financial markets is vast and complex; consequently, the development of systems that simplify decision-making is an essential endeavor. In this article, several intelligent systems are proposed and tested to predict the closing price of the IBEX 35 index using more than ten years of historical data and five distinct architectures for neural networks. A multi-layer perceptron was the first step, followed by a simple recurrent neural network, a gated recurrent unit network and two long-short-term memory (LSTM) networks. The results of the analyses performed on these models have demonstrated a powerful capacity for prediction. Additionally, the findings of this research point to the fact that the application of intelligent systems can simplify the decision-making process in financial markets, which is a substantial advantage. Furthermore, by comparing the predicted outcome errors between the models, the LSTM presents the lowest error with a higher computational time in the training phase. The LSTM was able to accurately forecast the closing price of the day as well as the price for the following one and two days in advance. In conclusion, the empirical results demonstrated that these models could accurately predict financial data for trading purposes and that the application of intelligent systems, such as the LSTM network, represents a promising advancement in financial technology.

The use of neural networks in the foresight process

The article considers scenarios of application of neural networks of different architectures to fulfill tasks in the foresight process. The purpose of the article is to determine at what stages of the foresight procedure the application of neural networks is justified and with what architecture. The differences between foresight and the process of forecasting are revealed. In addition, the concept of foresight, its main stages and phases, classification are considered. It is substantiated that the application of neural networks can significantly facilitate the foresight procedure at such stages as collection and processing of primary information, development of scenarios and solutions to problems, communication, and report preparation. It is shown that different types of neural networks are suitable for different foresight tasks. It is revealed that neural networks can process a larger amount of data and automatically detect complex patterns, which makes them more effective under conditions of environmental uncertainty and variability. The article ephasises the importance of further research and development of methods for applying neural networks in foresight processes with consideration to the specifics of particular industries and types of tasks. In the course of the research, the authors used analytical methods of diagnostics, establishing cause-and-effect relationships, etc.

The modeling of the Organic Molecules Rejection using the Bootstrap Aggregated Neural Networks for the evaluation of the Forward Osmosis Process performance

<p>The forward osmosis process is currently more studied to be a replacement for another consuming-energy process, for this, many works show up the rejection of different molecules, energy consumption, and modeling of different objectives related to FO process. Our study consists to model the rejection of organic molecules (neutral and ionic) by FO process; however, this paper is the simultaneous applications of the single neural network based on quantitative- structure properties relationship (QSPR-SNN) and the bootstrap aggregated neural network (BANN) to predict the rejection of 53 OM. According to the results obtained, the coefficient correlation "R" is used to evaluate the performance of each model for the unseen data, the QSPR-BANN gives R value equal to 0.9909 higher than the value of the SNN which is 0.9401, the Root Mean Square Error of the QSPR-BANN is less than that of the QSPR-SNN with values equal to 0.5764% and 1.2826% respectively.</p>

Development of Neural Networks to Study Flow Behavior of Medium Carbon Microalloyed Steel during Hot Forming

In the present article, the application of an artificial neural network (ANN) model whose function is the development of plastic instability maps of a medium carbon microalloyed steel during the hot forming process is studied. Secondly, we proceed to create another ANN capable of providing the recrystallized grain size in the steady state resulting from forming deformation. We start from the experimental data of a medium carbon microalloyed steel obtained by hot compression tests with strain rates that vary between 10−4 s−1 and 3 s−1 and in a range of temperatures between 900 °C and 1150 °C. These experimental data are used to train the proposed ANN and obtain flow curves. Finally, the processing maps are developed by applying the dynamic materials model (DMM), according to which the safe hot forming domains and the plastic instability domains of the studied material are delineated. The comparison between the ANN and the experimental maps is carried out. It is ascertained that the optimal regions of forging in the ANN maps coincide with those obtained in the experimental maps. In addition, a study of the influence of the microstructure on the behavior of the studied steel during hot forming is carried out.

Application of self-learning interval type-2 fuzzy neural network in PM2.5 concentration prediction

Abstract The change of PM2.5 concentration in air quality is nonlinear and difficult to predict. Therefore, a self-learning interval type-2 fuzzy neural network (SLIT2FNN) is proposed. SLIT2FNN has two parts: online structure learning and parameter learning. In structure learning, to improve the training accuracy and speed of the model, the Possibilistic Fuzzy C-Means (PFCM) algorithm is used to process the input data and obtain the number of initial rules before model training. The PFCM algorithm introduces the concept of possibility P to Fuzzy C-Means (FCM), allowing PFCM to overcome the shortcomings of FCM that cannot accurately cluster a large number of nonlinear problems. SLIT2FNN can establish an appropriate number of rules in the preparation stage, and then use the firing strength of the antecedents of the rules to judge whether to generate fuzzy rules for online self-learning, thereby optimizing its network structure. Then, the improved Levenberg–Marquardt (ILM) algorithm is used to modify the relevant parameters of SLIT2FNN. The ILM algorithm can address the challenge of numerous parameters in the Jacobian matrix and complex calculations and improve the calculation speed and adaptive ability of SLIT2FNN parameter learning. Finally, SLIT2FNN is applied to the prediction of air quality PM2.5 concentration, and the performance is compared with other models. The experiment proves that SLIT2FNN has a high prediction accuracy and fast convergence.

Neural Network Approach for Cholera Dynamics: Integrating Deterministic and Stochastic Insights

In this article, a comprehensive qualitative analysis framework is presented that integrates stochastic and deterministic models to explore the transmission dynamics of Cholera disease. The significance of the reproduction number in understanding the spread of the disease and in formulating effective control strategies is emphasized. The sensitivity analysis of model parameters is conducted to identify those that critically influence transmission. By converting the deterministic model into a stochastic form, Brownian motion and stochastic parameters are incorporated to capture the inherent randomness in disease dynamics. This approach is further enriched by the application of neural networks (NN) to simulate and validate the complex interactions involved in Cholera transmission. The analysis extends to the global positive solution, stochastic reproduction number, and virus-free stochastic dynamics, providing an improved understanding of the disease's behavior. The critical conditions necessary for the extinction and long-term elimination of the virus are also addressed, highlighting the importance of controlling its spread. The stationary distribution of the disease is examined through the lens of a regular Markov process, enhancing the understanding of the stochastic model's dynamics. The results verified by neural networks, compared with those obtained from conventional numerical methods, underscore the accuracy and versatility of neural networks in epidemiological research, offering new perspectives and methodologies for tackling this global health challenge.

Neuro-inspired hardware solutions for high-performance computing: A TiO2-based nano-synaptic device approach with backpropagation

Computer-based machine learning algorithms that produce impressive performance results are computationally demanding and thus subject to high energy consumption during training and testing. Therefore, compact neuro-inspired devices are required to achieve efficiency in hardware resource consumption for the smooth implementation of neural network applications that require low energy and area. In this paper, learning characteristics and performances of the nanoscale titanium dioxide (TiO2) based synaptic device have been analyzed by implementing it in the hardware-based neural network for digit classification. Our model is experimentally validated by using 32-nm CMOS technology and the results demonstrate that the model provides high computational ability with better accuracy and efficiency in resource consumption with low energy and less area. The proposed model exhibits 20% energy gain and 16.82% accuracy improvement and 18% less total latency compared to the state-of-the-art Ag:Si synaptic device-based neural network. Furthermore, when compared to the software-based (i.e., computer-based) implementation of neural networks, our TiO2-based model not only achieved an impressive accuracy rate of 90.01% on the MNIST dataset but also did so with reduced energy consumption. Consequently, our model, characterized by a low hardware implementation cost, emerges as a promising neuro-inspired hardware solution for various neural network applications. The proposed model has further demonstrated outstanding performance in experiments involving both the MNIST and Fisher’s Iris datasets. On the latter dataset, the model exhibited notable precision (94.5%), recall (91.5%), and an impressive F1-score (92.9%), accompanied by a commendable accuracy rate of 93.04%.

Unified predictive modeling of supercontinuum spectra: Using multi-material data with Closed-Form Continuous Time Neural Networks

This paper explores the application of the Closed-Form Continuous-Time Neural Networks (CfC) model in predicting supercontinuum spectra in a unified dataset of various core materials in a planar waveguide. Through numerical simulations and dataset generation, the study constructs a robust model capable of accurately predicting spectral behavior under different conditions and material variation. Initially, the unified dataset comprises spectral data for three materials: Silicon Nitride (Si3N4), Lithium Niobate (LiNbO3), and Silicon Carbide (SiC). The CfC model demonstrates remarkable accuracy in capturing spectral nuances and exhibits a minimal Mean Squared Error (MSE) loss value of 7.2537×10−4. Subsequently, the dataset is expanded to include Tantalum Pentoxide (Ta2O5), introducing a fourth material for evaluation. The inclusion of Ta2O5 data further validates the model’s scalability and generalization capabilities with Mean Squared Error (MSE) loss value of 6.7894×10−4. The advantage of the CfC model in precisely predicting supercontinuum spectra while retaining computational efficiency is demonstrated by comparisons with conventional methods. The CfC model is a viable tool for enhancing predictive modeling in photonics research because of its scalability and generalization characteristics. This will pave the way for future developments in deep learning techniques for optical device optimization.

Physics-informed neural networks for solving flow problems modeled by the 2D Shallow Water Equations without labeled data

This paper investigates the application of physics-informed neural networks (PINNs) to solve free-surface flow problems governed by the 2D shallow water equations (SWEs). Two types of PINNs are developed and analyzed: a physics-informed fully connected neural network (PIFCN) and a physics-informed convolutional neural network (PICN). The PINNs eliminate the need for labeled data for training by employing the SWEs, initial and boundary conditions as components of the loss function to be minimized. Results from a set of idealized and real-world tests showed that the prediction accuracy and computation time (i.e., training time) of both PINNs may be less affected by the resolution of the domain discretization when compared against solutions by a Finite Volume (FV) model. Overall, the PICN shows a better trade-off between computational speed and accuracy than the PIFCN. Also, our results for the idealized problems indicated that PINNs can provide more than 5 times higher prediction accuracy than the FV model, while the FV simulation with coarse resolution (e.g., 10 m) can provide sub-centimeter accurate (RMSE) solutions at least one order of magnitude faster than the PINNs.Results from a river flood simulation showed that PINNs delivered better speed-accuracy trade-off than the FV model in terms of predicting the water depth, while FV models outperformed the PINNs for predictions of total flow discharge.

Application of Deep Quantum Neural Networks to Finance

The recent development of quantum computing gives us an opportunity to explore its potential applications to many fields, with the field of finance being no exception. In this paper, we apply the deep quantum neural network proposed by Beer et al. (2020) and discuss such potential in the context of simple experiments, such as learning implied volatilities and option prices. Furthermore, Greeks, such as delta and gamma, which are important measures in risk management, can be computed analytically with the neural network, and our numerical experiments show that the deep quantum neural network is a promising technique for solving such numerical problems arising in finance.

Novel applications of Convolutional Neural Networks in the age of Transformers.

Convolutional Neural Networks (CNNs) have been central to the Deep Learning revolution and played a key role in initiating the new age of Artificial Intelligence. However, in recent years newer architectures such as Transformers have dominated both research and practical applications. While CNNs still play critical roles in many of the newer developments such as Generative AI, they are far from being thoroughly understood and utilised to their full potential. Here we show that CNNs can recognise patterns in images with scattered pixels and can be used to analyse complex datasets by transforming them into pseudo images with minimal processing for any high dimensional dataset, representing a more general approach to the application of CNNs to datasets such as in molecular biology, text, and speech. We introduce a pipeline called DeepMapper, which allows analysis of very high dimensional datasets without intermediate filtering and dimension reduction, thus preserving the full texture of the data, enabling detection of small variations normally deemed 'noise'. We demonstrate that DeepMapper can identify very small perturbations in large datasets with mostly random variables, and that it is superior in speed and on par in accuracy to prior work in processing large datasets with large numbers of features.

Probabilistic neural networks for incremental learning over time-varying streaming data with application to air pollution monitoring

This paper proposes a novel algorithm for incremental learning over streaming data in a non-stationary environment. The idea refers to the applicability of Probabilistic Neural Networks (PNNs), commonly used as a fast and robust method for solving classification problems in a stationary scenario. It is well known that PNNs have solid mathematical foundations but they fail in the non-stationary scenario and are not able to deal with concept drift. In this paper, the method based on the orthogonal series expansions of unknown probability densities is proposed. This approach significantly extends the applicability of the PNNs. The nonparametric procedures called Incremental Probabilistic Neural Networks (IPNNs) for tracking drifting probability densities or conditional class densities, in the case of classification, are presented. We prove their convergence as the stream data size is growing to infinity. More precisely, we show convergence in probability and with probability one as the sample size tends to infinity. Compared to the existing literature, almost exclusively based on various heuristics, the proposed method is mathematically justified and has solid theoretical foundations. Simulations performed on synthetic and air pollution data confirm the effectiveness of the algorithm.

Application of convolutional neural networks in medical images: a bibliometric analysis.

In the field of medical imaging, the rapid rise of convolutional neural networks (CNNs) has presented significant opportunities for conserving healthcare resources. However, with the wide spread application of CNNs, several challenges have emerged, such as enormous data annotation costs, difficulties in ensuring user privacy and security, weak model interpretability, and the consumption of substantial computational resources. The fundamental challenge lies in optimizing and seamlessly integrating CNN technology to enhance the precision and efficiency of medical diagnosis. This study sought to provide a comprehensive bibliometric overview of current research on the application of CNNs in medical imaging. Initially, bibliometric methods were used to calculate the frequency statistics, and perform the cluster analysis and the co-citation analysis of countries, institutions, authors, keywords, and references. Subsequently, the latent Dirichlet allocation (LDA) method was employed for the topic modeling of the literature. Next, an in-depth analysis of the topics was conducted, and the topics in the medical field, technical aspects, and trends in topic evolution were summarized. Finally, by integrating the bibliometrics and LDA results, the developmental trajectory, milestones, and future directions in this field were outlined. A data set containing 6,310 articles in this field published from January 2013 to December 2023 was complied. With a total of 55,538 articles, the United States led in terms of the citation count, while in terms of the publication volume, China led with 2,385 articles. Harvard University emerged as the most influential institution, boasting an average of 69.92 citations per article. Within the realm of CNNs, residual neural network (ResNet) and U-Net stood out, receiving 1,602 and 1,419 citations, respectively, which highlights the significant attention these models have received. The impact of coronavirus disease 2019 (COVID-19) was unmistakable, as reflected by the publication of 597 articles, making it a focal point of research. Additionally, among various disease topics, with 290 articles, brain-related research was the most prevalent. Computed tomography (CT) imaging dominated the research landscape, representing 73% of the 30 different topics. Over the past 11 years, CNN-related research in medical imaging has grown exponentially. The findings of the present study provide insights into the field's status and research hotspots. In addition, this article meticulously chronicled the development of CNNs and highlighted key milestones, starting with LeNet in 1989, followed by a challenging 20-year exploration period, and culminating in the breakthrough moment with AlexNet in 2012. Finally, this article explored recent advancements in CNN technology, including semi-supervised learning, efficient learning, trustworthy artificial intelligence (AI), and federated learning methods, and also addressed challenges related to data annotation costs, diagnostic efficiency, model performance, and data privacy.