Network Based Prediction Model Research Articles

Stock Price Prediction Using LSTM

Wealth management tools manage and assign families, individuals, enterprises, and institutions to achieve the purpose of increasing and maintaining value to accelerate asset growth. Among them, in investment and financial management, favourite product of people for investment often stocks, because the stock market has great advantages and charm, especially compared with other investment methods. Designing robust and accurate predictive models for stock price prediction has been an active area of research over a long time. Developing an accurate stock prediction method can help investors in making profitable decisions by reducing the investment risks. Our proposition includes a regression model built on long-and-short-term memory (LSTM) network-based predictive models. These spatial features are then fed into LSTM layers, which capture temporal dependencies and long-range correlations in the time series data. The combination of these two architectures enhances the model's ability to capture both short-term fluctuations and long-term trends in stock prices. This system will provide accurate outcomes in comparison to currently available stock price predictor algorithms. The network is trained and evaluated with various sizes of input data to urge the graphical outcomes. This system will provide accurate outcomes in comparison to currently available stock price predictor algorithms Keywords: Long and Short-Term Memory, Time-Series Data, Recurrent Neural Network.

Artificial neural network-based model for sleep quality prediction for frontline medical staff during major medical assistance.

Background: The sleep quality of medical staff was severely affected during COVID-19, but the factors influencing the sleep quality of frontline staff involved in medical assistance remained unclear, and screening tools for their sleep quality were lacking. Methods: From June 25 to July 14, 2022, we conducted an Internet-based cross-sectional survey. The Pittsburgh Sleep Quality Index (PSQI), a self-designed general information questionnaire, and a questionnaire regarding the factors influencing sleep quality were combined to understand the sleep quality of frontline medical staff in Fujian Province supporting Shanghai in the past month. A chi-square test was used to compare participant characteristics, and multivariate unconditional logistic regression analysis was used to determine the predictors of sleep quality. Stratified sampling was used to divide the data into a training test set (n = 1061, 80%) and an independent validation set (n = 265, 20%). Six models were developed and validated using logistic regression, artificial neural network, gradient augmented tree, random forest, naive Bayes, and model decision tree. Results: A total of 1326 frontline medical staff were included in this survey, with a mean PSQI score of 11.354 ± 4.051. The prevalence of poor sleep quality was 80.8% (n = 1072, PSQI >7). Six variables related to sleep quality were used as parameters in the prediction model, including type of work, professional job title, work shift, weight change, tea consumption during assistance, and basic diseases. The artificial neural network (ANN) model produced the best overall performance with area under the curve, accuracy, sensitivity, specificity, precision, F1 score, and kappa of 71.6%, 68.7%, 66.7%, 69.2%, 34.0%, 45.0%, and 26.2% respectively. Conclusions: In this study, the ANN model, which demonstrated excellent predictive efficiency, showed potential for application in monitoring the sleep quality of medical staff and provide some scientific guidance suggestions for early intervention.

An integrated convolutional neural network-based surrogate model for crashworthiness performance prediction of hot-stamped vehicle panel components

During the structural design of vehicle components, Finite Element (FE) modelling has been extensively used for simulations of physical experiments. A typical design optimisation task requires iterative simulations to identify the optimum design, where FE simulations can be too time-consuming. Surrogate models have been developed to approximate complex simulations, which can reduce computational time and improve the efficiency of the design cycle. This paper presents a novel application of convolutional neural network (CNN) on rapid predictions of crashworthiness performance of vehicle panel components considering manufacturability. The dataset for training the model was generated based on the FE results of hot-stamped ultra-high strength steel (UHSS) B-pillar components. The formed components were analysed with a simplified lateral crash test to evaluate the deformation under impact. The trained model can instantly predict the deformation of the designed component with high accuracy compared to the FE results. Due to its high computational efficiency and precision, the surrogate model enables faster and more extensive design evaluations.

Maize yield prediction with trait-missing data via bipartite graph neural network.

The timely and accurate prediction of maize (Zea mays L.) yields prior to harvest is critical for food security and agricultural policy development. Currently, many researchers are using machine learning and deep learning to predict maize yields in specific regions with high accuracy. However, existing methods typically have two limitations. One is that they ignore the extensive correlation in maize planting data, such as the association of maize yields between adjacent planting locations and the combined effect of meteorological features and maize traits on maize yields. The other issue is that the performance of existing models may suffer significantly when some data in maize planting records is missing, or the samples are unbalanced. Therefore, this paper proposes an end-to-end bipartite graph neural network-based model for trait data imputation and yield prediction. The maize planting data is initially converted to a bipartite graph data structure. Then, a yield prediction model based on a bipartite graph neural network is developed to impute missing trait data and predict maize yield. This model can mine correlations between different samples of data, correlations between different meteorological features and traits, and correlations between different traits. Finally, to address the issue of unbalanced sample size at each planting location, we propose a loss function based on the gradient balancing mechanism that effectively reduces the impact of data imbalance on the prediction model. When compared to other data imputation and prediction models, our method achieves the best yield prediction result even when missing data is not pre-processed.

Optical materials discovery and design with federated databases and machine learning.

Combinatorial and guided screening of materials space with density-functional theory and related approaches has provided a wealth of hypothetical inorganic materials, which are increasingly tabulated in open databases. The OPTIMADE API is a standardised format for representing crystal structures, their measured and computed properties, and the methods for querying and filtering them from remote resources. Currently, the OPTIMADE federation spans over 20 data providers, rendering over 30 million structures accessible in this way, many of which are novel and have only recently been suggested by machine learning-based approaches. In this work, we outline our approach to non-exhaustively screen this dynamic trove of structures for the next-generation of optical materials. By applying MODNet, a neural network-based model for property prediction, within a combined active learning and high-throughput computation framework, we isolate particular structures and chemistries that should be most fruitful for further theoretical calculations and for experimental study as high-refractive-index materials. By making explicit use of automated calculations, federated dataset curation and machine learning, and by releasing these publicly, the workflows presented here can be periodically re-assessed as new databases implement OPTIMADE, and new hypothetical materials are suggested.

Improving the Computerized Ionospheric Tomography Performance Through a Neural Network-Based Initial IED Prediction Model

Improving the Computerized Ionospheric Tomography Performance Through a Neural Network-Based Initial IED Prediction Model

Improved Generative Adversarial Network Stock Price Prediction Method

In response to the challenges posed by the nonlinearity, instability, and complexity of the stock market in the insurance industry, we propose an enhanced generative adversarial neural network-based stock prediction model termed CAL-WGAN-GP. The model's generator incorporates components such as the CNN-BiLSTM model and a self-attention mechanism, employed to generate precise predictions for stock closing prices. The discriminator, comprising a multi-layer convolutional neural network, is tasked with distinguishing between the stock closing prices generated by the generator and actual stock closing prices. To assess the model's generalization capability, stock data from China Ping an, China Life, XinHua Insurance, and Pacific Insurance is selected. During the dataset construction, relevant features, including technical indicators, are incorporated to facilitate the model in better learning hidden data information. Experimental results demonstrate that CAL-WGAN-GP urpasses baseline models across four evaluation metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R2), achieving the highest degree of data fitting

Development of 1D-convolutional Neural Network-based Height Profile Prediction Model in Directed Energy Deposition Process Using Melt-pool Image Data

Directed energy deposition (DED) process is a representative metal additive manufacturing technology that uses a flexible deposition head mainly used for repairs in space and marine industries. The DED process saves time and money as it repairs only damaged parts and components. Therefore, a geometric control is important to fill the volume of the target damaged area economically and accurately. However, efficiency depends on process parameters such as laser power, scanning speed. This study proposes a one-dimensional convolutional neural network (1D-CNN) model to predict the height profile of the DED parts utilizing melt-pool image data. First, DED experiments were performed for a total of nine cases considering laser power and scanning speed as parameters. The collected melt-pool image data was pre-processed and only those related to the regions of interest were extracted. Initially, a total of 15 features were extracted from size, shape, location, and brightness from the melt-pool images. Then, 10 critical ones, selected through a permutation feature importance evaluation method, were input to the 1D-CNN algorithm to predict height profiles of the deposited layers. In testing phase, a mean absolute percentage error (MAPE) of 9.55% was achieved, and thus, applicability of the proposed model was verified.

A Convolutional Neural Network-Based Predictive Model for Assessing the Learning Effectiveness of Online Courses Among College Students

A Convolutional Neural Network-Based Predictive Model for Assessing the Learning Effectiveness of Online Courses Among College Students

Estimation of cohesion for intact rock materials using regression and soft computing analyses

Shear strength parameters such as cohesion (c) and internal friction angle (ϕ) are among the most critical rock properties used in the geotechnical design of most engineering projects. However, the determination of these properties is laboring and requires special equipment. Therefore, this study introduces several predictive models based on regression and artificial intelligence methods to estimate the c of different rock types. For this purpose, a comprehensive literature survey is carried out to collect quantitative data on the shear strength properties of different rock types. Then, regression and soft computing analyses are performed to establish several predictive models based on the collected data. As a result of these analyses, five different predictive models (M1–M5) were established. Based on the performance of the established predictive models, the artificial neural network-based predictive model (model 5, M5) was the most suitable choice for evaluating the c for different rock types. In addition, mathematical expressions behind the M5 model are also presented in this study to allow users to implement it more efficiently. In this regard, the present study can be declared a case study showing the applicability of regression and soft computing analyses to evaluate the c of different rock types. However, the number of datasets used in this study should be increased to get more comprehensive predictive models in future studies.

Artificial neural network-based prediction model of elastic floor response spectra incorporating dynamic primary-secondary structure interaction

The evaluation of the Floor Response Spectrum (FRS) holds paramount significance in assessing the seismic behavior of secondary structures. Precise FRS prediction empowers engineers to make informed decisions concerning structural design, retrofitting, and safety precautions. This study aims to scrutinize the impact of dynamic interaction between primary and secondary structures on FRS. Both the elastic primary structure (PS) and elastic secondary structure (SS) employ a single-degree-of-freedom (SDOF) system. Governing motion equations for both coupled (with dynamic interaction) and uncoupled (without dynamic interaction) systems are formulated and solved numerically. The study investigates how variations in the vibration period of PS (Tp), tuning ratio (Tr), mass ratio (μ), and damping ratio (ξs) of SS influence FRS. The FRS impact remains minimal at μ = 0.001 (0.1%); however, with increasing mass ratio, PS-SS dynamic interaction significantly affects SS's spectral acceleration response. Coupled analysis is crucial only for secondary structures tuned to the primary structure's vibration period (0.8≤Tr≤1.2). This study utilizes two-layer feed-forward Artificial Neural Networks (ANNs) for FRS prediction. The Levenberg-Marquardt (LM) backpropagation (BP) algorithm trains the network using a comprehensive dataset. In summary, it is evident that the ANNs, once trained, enable accurate prediction of the FRS, exhibiting a R2 of 99%. Additionally, a design expression is formulated utilizing the ANN model and subsequently compared with the existing formulation.

Multi-Term Electrical Load Forecasting of Smart Cities Using a New Hybrid Highly Accurate Neural Network-Based Predictive Model

Multi-Term Electrical Load Forecasting of Smart Cities Using a New Hybrid Highly Accurate Neural Network-Based Predictive Model

Artificial Neural Network-Based Prediction Model Back Propagation on Blood Demand and Blood Supply

The balance between blood demand and supply at the Indonesian Red Cross Blood Transfusion Unit (UTD-PMI) is crucial. This condition must be maintained to reduce unused or expired blood supplies. Despite the situation in UTD-PMI, where the blood supply exceeds demand, there is still a shortage of blood when needed by patients. This research aims to model the prediction of blood demand and supply for each blood type using the Back Propagation artificial neural network approach. Data from the last 3 years, from 2020 to 2022, were utilized in this research process. There are three stages in this research process. The first stage involves the training process, using data from January 2020 to December 2021. The testing process utilizes data from January 2021 to December 2022. The prediction process involves displaying the forecasted data for the next 12 months from January to December 2023. The accuracy of the calculations is assessed using the mean square error (MSE). Ultimately, the research results present the prediction model for the four types of blood with respect to the demand and supply. These findings can serve as a reference to regulate future blood donation activities carried out by the UTD-PMI.

A neural network-based prediction model for cultivating skilled personnel in higher vocational education

Abstract In this paper, the neurons in the BP neural network are used to represent the skill-based talent cultivation feature vectors, and the feature vectors are trained on the network to obtain the vector transformation function. On the basis of the vector transformation function, after constructing the technical talent cultivation prediction model by using the backpropagation algorithm, the data indicators are determined according to the requirements of skill-based talent cultivation, and the initial data are normalized by overfitting for the technical talent cultivation prediction results. The empirical research on the synthesis of technically skilled talents in higher vocational education is designed by means of questionnaires, and the data analysis software is used to analyze the examples of skilled talent cultivation in vocational education under the background of big data technology. The results show that from 2015 to 2020, the predicted values of the number of technically skilled talents demanded in a province are 92,130, 105,396, 160,946, 225,045, 232,313 and 216,150 respectively, and the relative error values are less than 0.05 compared with the actual demand values of technically skilled talents in the same period, indicating that based on the BP neural network-based technical talent cultivation prediction model outputs a good fit between the extrapolation test prediction value and the real value. This study guides the cultivation of skilled talents in higher vocational education.

Thermal displacement prediction of variable preload motorized spindles based on speed reduction experiments and IABC-BP optimization models

The thermal error caused during the high-speed operation of a high-speed motorized spindle has a significant impact on machine tool precision. In this paper, we firstly built, constructed an experimental platform for variable voltage preloaded motorized spindle, used the natural deceleration experimental method to ascertain the spindle's thermal displacement and temperature information when bearing preload is 1400 N, 1450 N, 1550 N and 1700 N, and combined with the thermoelasticity theoretical analysis, the thermal displacement of affected by the heat generation of motor and bearing was separated, and a new artificial bee colony algorithm-optimized BP neural network-based thermal error prediction model has been presented. The thermal displacements of the spindles are separated and a BP neural network optimization of a novel thermal error prediction model based on Improved Artificial Bee Colony Algorithm (IABC-BP) is proposed for transformer preloaded spindles. Combined with the experimental data of bearing preload of 1400 N, the thermal displacements of the spindle at preloads of 1450 N, 1550 N and 1700 N are predicted, and the evaluation indexes obtained from the simulation of the BP, ABC-BP, and IABC-BP models are compared. absolute error (MAE) and root-mean-square error (RMSE), higher goodness-of-fit (R2), and 20.37 % lower mean absolute error and 26.83 % lower root-mean-square error compared with the traditional thermal error prediction model. The IABC-BP prediction model proposed in this paper provides a more accurate compensation method for transformer preloaded spindles.

A Deep Neural Network-Based Assistive Decision Method for Financial Risk Prediction in Carbon Trading Market

The price of carbon emission rights in the market fluctuates greatly due to various factors from economy, finance, and climate. For an enterprise that needs to conduct carbon trading activities, it is extremely necessary to fully grasp the price of carbon trading in the future period. Thus in this paper, a deep neural network-based assistive decision model for financial risk prediction in carbon trading market is proposed for this purpose. Specifically, the dynamic risk spillover effects of domestic and international carbon trading markets are studied, and a frontier time-varying model is utilized to measure the risk spillover effects. Then, the deep neural network is used for quantitative research and to construct an intelligent decision scheme that outputs financial risk prediction results. Four perspectives, energy price, climate environment, carbon market price, and macroeconomics, are selected as the input to analyze the influence factors of carbon emission rights price. Finally, several linear regression models are adopted as the baseline methods for comparison, and experimental results show that the proposed method can achieve better prediction performance compared with baseline methods.

MtADENet: A novel interpretable method integrating multiple types of network-based inference approaches for prediction of adverse drug events

Identification of adverse drug events (ADEs) is crucial to reduce human health risks and accelerate drug safety assessment. ADEs are mainly caused by unintended interactions with primary or additional targets (off-targets). In this study, we proposed a novel interpretable method named mtADENet, which integrates multiple types of network-based inference approaches for ADE prediction. Different from phenotype-based methods, mtADENet introduced computational target profiles predicted by network-based methods to bridge the gap between chemical structures and ADEs, and hence can not only predict ADEs for drugs and novel compounds within or outside the drug-ADE association network, but also provide insights for the elucidation of molecular mechanisms of the ADEs caused by drugs. We constructed a series of network-based prediction models for 23 ADE categories. These models achieved high AUC values ranging from 0.865 to 0.942 in 10-fold cross validation. The best model further showed high performance on four external validation sets, which outperformed two previous network-based methods. To show the practical value of mtADENet, we performed case studies on developmental neurotoxicity and cardio-oncology, and over 50 % of predicted ADEs and targets for drugs and novel compounds were validated by literature. Moreover, mtADENet is freely available at our web server named NetInfer (http://lmmd.ecust.edu.cn/netinfer/). In summary, mtADENet would be a powerful tool for ADE prediction and drug safety assessment in drug discovery and development.

A knowledge transfer online stochastic configuration network-based prediction model for furnace temperature in a municipal solid waste incineration process

To alleviate the concept drift of an offline prediction model for the furnace temperature in a municipal solid waste incineration (MSWI) process caused by changes in working conditions, a prediction method for the furnace temperature based on a knowledge transfer online stochastic configuration network is proposed in this work. The proposed method includes offline learning and online learning. First, a stochastic configuration network is utilized to construct the offline furnace temperature prediction model, and a knowledge transfer method is employed to update the model under new operating conditions in the offline learning stage. Then, the updated model is used as the initial state of online modeling. Second, the recursive solution of the model output weights is presented to adapt to the dynamic change in incineration conditions, and a direction forgetting mechanism is utilized to enhance the result of the prediction model for the furnace temperature under nonpersistence of excitation in the online stage. Finally, to further verify the proposed online modeling method, the real historical data of an MSWI plant are utilized to finish the comparative experiments. The experimental results with the other methods show that the proposed prediction method for the furnace temperature presents a smaller error. Hence, the proposed method can reduce the influence of working conditions on the accuracy of furnace temperature prediction models.

Research on the Prediction Method of Clock Tester Calibration Data Based on Radial Basis Function Neural Network

A radial basis function (RBF) neural network-based calibration data prediction model for clock testers is proposed to address the issues of fixed calibration cycles, low efficiency, and waste of electrical energy. This provides a new method for clock tester traceability calibration. First, analyze the mechanism of clock tester calibration parameters and the influencing factors of prediction targets. Based on the learning rules of an RBF neural network, determine the data types of training and testing sets. Second, normalize the training and testing data to avoid the adverse effects of data characteristics and distribution differences on the prediction model. Finally, based on different prediction objectives, time-driven and data-driven calibration data prediction models are constructed using RBF neural networks. Through simulation analysis, it is shown that an RBF neural network is superior to a BP neural network in predicting clock tester calibration data, and time-driven prediction accuracy is superior to data-driven prediction accuracy. Moreover, the prediction error and mean square error of both prediction models are on the order of 10−9, meeting the prediction accuracy requirements.

Variability of total alkalinity in coastal surface waters determined using an in-situ analyzer in conjunction with the application of a neural network-based prediction model

Total alkalinity (TA) is an important variable of the ocean carbonate system. In coastal oceans, carbonate system dynamics are controlled by a range of processes including photosynthesis and respiration, calcification, mixing of water masses, continental inputs, temperature changes, and seasonal upwelling. Assessments of diel, seasonal and interannual variations in TA are required to understand the carbon cycle in coastal oceans. However, our understanding of these variations remains underdeveloped due to limitations in observational techniques. Autonomous TA measurements are therefore required. In this study, an in situ TA analyzer (ISA-TA) based on a single-point titration with spectrophotometric pH detection was deployed in Tong'an Bay, Xiamen, China, over a five-month period in 2021 to determine diel and seasonal TA variations. The TA observations were combined with an artificial neural network (ANN) model to construct TA prediction models for this area. This provided a simple method to investigate TA variations in this region and was applied to predict surface water TA between March and April 2021. The in situ TA observations showed that TA values in Tong'an Bay varied within a range from 1931 to 2294 μmol kg−1 over the study period, with low TA in late winter, early summer and late summer, and high TA in early winter. The TA variations in late summer and early winter were mainly controlled by mixing of water bodies. The diel variations of TA were greatly determined by tides, with a diel amplitude of 9 to 247 μmol kg−1. The ANN model used temperature, salinity, chlorophyll, and dissolved oxygen to estimate TA, with a root-mean-square error (RMSE) of ∼14 μmol kg−1, with salinity as the input variable with the greatest weight. The approach of combining ISA-TA observations with an ANN model can be extended to study the carbonate system in other coastal regions.