Index Prediction Model Research Articles

Development of Remodeling Index Prediction Model of Deteriorated Asphalt Pavements for Large-Scale Repair Works

Development of Remodeling Index Prediction Model of Deteriorated Asphalt Pavements for Large-Scale Repair Works

A hybrid prediction model of blast furnace permeability index combining least square support vector machine and artificial neural network

Blast furnace (BF) permeability index is a crucial parameter that can quickly, intuitively, and comprehensively reflect the furnace condition. Accurate prediction of this index is crucial for optimising production efficiency and ensuring the stable operation of the BF. In this study, a hybrid permeability index prediction model is constructed by combining a least squares support vector machine and an artificial neural network, using the mean shift clustering algorithm (MSCA) to classify the BF conditions is applied. The results show that the MSCA algorithm shows remarkable precision in classifying the stable and unstable operating states of BF, achieving an impressive accuracy rate of 93.98%. The hybrid prediction model could accurately predict the permeability index and has a mean absolute error of 0.6877, a mean square error of 0.4721 and an R2 of 0.9215, highlighting its robust predictive performance. These findings underscore the practical significance of our model in enhancing BF operational efficiency and reliability.

Performance evaluation of housing price index prediction model using DNN and SVR

This study used the base interest rate, mortgage interest rate, deposit interest rate, consumer price index, exchange rate, and composite stock price index as variables to predict the housing price index. The variables were normalized using the min-max normalization method. Machine learning methods, Deep Neural Networks (DNN) and Support Vector Regression (SVR), were employed to construct a prediction model, and the fit of the model was evaluated using the Root Mean Square Error (RMSE). The analysis results of the DNN model indicated that when applying the softplus activation function, the RMSE was 0.1298, resulting in the smallest prediction error, and the correlation coefficient between the predicted and actual values was highest at 0.9342. The analysis results of the SVR model using the Gaussian RBF kernel showed that the RMSE was smallest at 0.2781 when the parameters were set to C=100 and Gamma=0.1. Therefore, the DNN model was found to be more fit for predicting the housing price index. Additionally, it was confirmed that the consumer price index had a non-linear effect with a positive relationship, and the base interest rate had a linear effect with a negative relationship.

Index Prediction Model Based on LASSO-PCA and Deep Learning

Index Prediction Model Based on LASSO-PCA and Deep Learning

Integrating plasma exosomal miRNAs, ultrasound radiomics and tPSA for the diagnosis and prediction of early prostate cancer: a multi-center study.

This multi-center study aims to explore the roles of plasma exosomal microRNAs (miRNAs), ultrasound (US) radiomics, and total prostate-specific antigen (tPSA) levels in early prostate cancer detection. We analyzed the publicly available dataset GSE112264 to identify the differentially expressed miRNAs associated with prostate cancer. Then, PyRadiomics was used to extract image features, and least absolute shrinkage and selection operator (LASSO) was used to screen the data. Subsequently, according to strict inclusion and exclusion criteria, the internal dataset (n = 199) was used to construct a diagnostic model, and the receiver operating characteristic (ROC) curve, calibration curve, decision curve analysis (DCA), and DeLong test were used to evaluate its diagnostic performance. Finally, we used an external dataset (n = 158) for further validation. The number of features extracted by PyRadiomics was 851, and the number of features screened by LASSO was 23. We combined the hsa-miR-320c, hsa-miR-944, radiomics, and tPSA features to construct a joint model. The area under the ROC curve of the combined model was 0.935. In the internal validation, the area under the curve (AUC) of the training set was 0.943, and the AUC of the test set was 0.946. The AUC of the external data set was 0.910. The calibration curve and decision curve were consistent with the performance of the combined model. There was a significant difference in the prediction ability between the combined prediction model and the single index prediction model, indicating the high credibility and accuracy of the combined model in predicting PCa. The combined prediction model, consisting of plasma exosomal miRNAs (hsa-miR-320c and hsa-miR-944), US radiomics, and clinical tPSA, can be utilized for the early diagnosis of prostate cancer.

Compressibility characteristics of municipal solid waste considering multiple factors.

Borehole samples were collected from a municipal solid waste (MSW) landfill in Xi'an, China, and subjected to a series of basic geotechnical and compression tests. This study aims to investigate the influence of composition, dry unit weight, moisture content, organic content, and landfill age on the compressibility of MSW. The results show that with increasing landfill age, the compressible components and organic content exhibit a decreasing trend while the dry unit weight increases. The moisture content does not vary significantly. There is also a linear trend between the logarithm of the primary compression strain and vertical stress. In addition, with an increase in compressible components content, moisture content, and organic content, the modified primary compression index (Cc') shows an increasing trend, whereas with an increase in dry unit weight and landfill age, Cc' shows a decreasing trend. Furthermore, regarding the 34 sets of data, authors only selected five data points for a detailed comparative analysis, this decision was made on the basis that these data points are representative. A modified primary compression index prediction model that considers the dry unit weight, moisture content, and landfill age of the MSW as influencing factors results in a fitting coefficient of 0.797. The Cc' values in this study are within the range of 0.12 to 0.36. These findings provide a reference for the vertical expansion design of existing landfills.

Air Quality Index Prediction Using DNN-Markov Modeling

ABSTRACT Air quality measurements contribute to diverse socio-economic sectors, including the environment and healthcare. Many methods are commonly applied to present air-quality levels, reflecting differing national standards. This study presents an air quality index prediction model, to measure air pollution levels for healthcare applications in congested areas. DNN-Markov modeling techniques are used to predict air quality, based on environmental conditions at peak hours. The developed model presents different approaches for highly accurate prediction of the air quality index for the next hour at a given location, under specific environmental conditions. This system could be used to support planning decisions related to the consequences of air quality. The study was conducted in selected locations in Jordan and England as a comparative model prediction accuracy study using different big-data sets of multivariate time series in traffic-heavy locations. The air quality index was represented using Neuro Fuzzy Logic as a method to contribute in air quality index predictions within blurry (boundary) values. The selected DNN-Markov hybrid model could predict air quality with accuracy of around (RMSE 7.86) for the location in England, and around (RMSE 15.27) for the one in Jordan.

Enhanced Air Quality Prediction Using a Coupled DVMD Informer-CNN-LSTM Model Optimized with Dung Beetle Algorithm.

Accurate prediction of air quality is crucial for assessing the state of the atmospheric environment, especially considering the nonlinearity, volatility, and abrupt changes in air quality data. This paper introduces an air quality index (AQI) prediction model based on the Dung Beetle Algorithm (DBO) aimed at overcoming limitations in traditional prediction models, such as inadequate access to data features, challenges in parameter setting, and accuracy constraints. The proposed model optimizes the parameters of Variational Mode Decomposition (VMD) and integrates the Informer adaptive sequential prediction model with the Convolutional Neural Network-Long Short Term Memory (CNN-LSTM). Initially, the correlation coefficient method is utilized to identify key impact features from multivariate weather and meteorological data. Subsequently, penalty factors and the number of variational modes in the VMD are optimized using DBO. The optimized parameters are utilized to develop a variationally constrained model to decompose the air quality sequence. The data are categorized based on approximate entropy, and high-frequency data are fed into the Informer model, while low-frequency data are fed into the CNN-LSTM model. The predicted values of the subsystems are then combined and reconstructed to obtain the AQI prediction results. Evaluation using actual monitoring data from Beijing demonstrates that the proposed coupling prediction model of the air quality index in this paper is superior to other parameter optimization models. The Mean Absolute Error (MAE) decreases by 13.59%, the Root-Mean-Square Error (RMSE) decreases by 7.04%, and the R-square (R2) increases by 1.39%. This model surpasses 11 other models in terms of lower error rates and enhances prediction accuracy. Compared with the mainstream swarm intelligence optimization algorithm, DBO, as an optimization algorithm, demonstrates higher computational efficiency and is closer to the actual value. The proposed coupling model provides a new method for air quality index prediction.

Hybrid seismic vulnerability models for regional structures considering bivariate intensity measures

The multiple-probability decision-making method for earthquake hazards considers multiple performance indicators and can be used to effectively estimate the seismic risk of structures. The seismic vulnerability model directly affects the development of the earthquake risk distribution in regional structures. This paper innovatively developed a bivariate intensity measurement method based on macroscopic and instrumental seismic intensities. An optimized instrument intensity calculation model was established considering the actual monitoring data of historical earthquakes in China. A hybrid seismic vulnerability quantification method based on empirical, expert judgement and analysis has been proposed and applied to evaluate the vulnerability levels of three types of building clusters in two typical earthquakes in Qinghai Province, China (the 2008 Dachaidan (DCD) earthquake and the 2009 Haixi (HX) earthquake). A structural hybrid vulnerability matrix and surface for nine zones based on bivariate intensity measures were developed. A synthetic vulnerability membership index considering fuzzy failure criteria and decision theory was proposed, and vulnerability membership curves for different vulnerability levels were established. An improved earthquake economic loss prediction function is proposed, and synthetic economic vulnerability index prediction models for three typical buildings in different regions are established. The estimated and calculated results of the developed multiscale variable parameter synthetic vulnerability model are highly consistent with the actual earthquake loss observations.

Research on Pricing and Replenishment of Vegetables Based on Grey Relational Model and Seasonal Index Prediction Model

This article mainly studies the problem of automatic pricing and replenishment decisions for vegetable products in supermarkets. A grey correlation model and ARIMA time series model are comprehensively established, and based on clustering analysis and regression analysis methods, the distribution patterns of sales volume for each vegetable category and item over time, as well as the relationship with cost plus pricing and mutual correlation, are analyzed to make reasonable predictions for future sales volume. In order to make decisions on product pricing, sales combination, and replenishment, and maximize supermarket profits, the data is preprocessed through normal test and quartile method. Through screening and sorting analysis, the distribution patterns of sales volume for each vegetable category and item over time are obtained; In order to analyze the relationship between different categories of vegetables and between different single products, a grey correlation model is established to determine the analysis sequence, and the correlation coefficients between each category and each single product are calculated to analyze the mutual relationship. And combined with the hierarchical clustering analysis method, the vegetable categories were divided into three sales types: high, medium, and low, expanding the relationship between categories. At the same time, a periodic chart was drawn to determine the periodicity of sales volume distribution in each category. Then, statistical analysis was conducted on the data to determine the linear correlation between sales volume and cost plus pricing. Based on this, a linear regression model was established to analyze the linear relationship between sales volume and cost plus pricing for the six categories; In order to provide the total daily replenishment amount and pricing strategy for the next week, this article establishes a seasonal index prediction model for sales forecasting. Combining the seasonal distribution of each category, the seasonal index is used to predict the sales volume for the next week. Considering the goal of maximizing profits, the target function is listed to comprehensively analyze the replenishment and pricing strategy for the next week.

Automatic Pricing and Replenishment Decision-Making for Vegetable Commodities Based on Seasonal Index Prediction Models

This study provides an in-depth analysis of the relationship between sales, pricing, and product categories to construct a predictive model designed to optimize replenishment decisions and maximize superstore profits. The study begins with data preprocessing, integrating data coded according to individual products, on which the model is built and solved. In the first part, descriptive statistical analysis and visualization revealed that the sales volume of each category showed a cluster-like distribution, which was affected by seasonal variations. Based on the time series smoothness test, it is initially judged that each individual product is a smooth series, and the smoothness of the series is verified by ADF test. In the second part, the correlation coefficients of the sales volume of each category and single product were calculated by using Spearman correlation analysis, and the results were presented through heat maps, which revealed the strong correlation between different categories. For the relational equation between total sales volume and cost-plus pricing, an autoregressive and least squares model was developed, with cost-plus pricing as the dependent variable and total sales volume as the independent variable. For the seasonal index prediction model, the total daily replenishment and pricing at future dates were predicted by calculating the seasonal index. The results show that the replenishment volume of flowers and leaves fluctuates greatly, and it is recommended that pricing and replenishment volume be adjusted in a timely manner according to the actual sales situation; cauliflower, aquatic roots and tubers, and eggplant are relatively stable, and they should be adjusted moderately according to the market demand; and chili peppers and edibles are on a downward trend, and it is recommended that replenishment volume be reduced in order to avoid the inventory backlog.

News-driven stock market index prediction based on trellis network and sentiment attention mechanism

Applying deep learning, especially time series neural network, to stock market prediction, has become one of the important applications in the quantitative finance field. However, due to the multi-correlation and volatility of the stock market, how to timely and accurately predict it has become a challenging issue. In order to cope with this challenge, a news-driven stock market index prediction model based on TrellisNet and a sentiment attention mechanism (SA-TrellisNet) is proposed. A sentiment analysis model based on CNN and LSTM is presented to obtain the sentiment index of massive news crawled from authoritative financial websites. Furthermore, a sentiment attention mechanism is designed for data fusion of stock data and news sentiment index as the input of the simple and efficient TrellisNet network for model training and prediction. The performance of our model is systematically evaluated using seven major international stock market indices including S&P500, NYSE, DJI, NASDAQ, FTSE 100, Nikkei 225 and SSE, and comparative experiments demonstrate that SA-TrellisNet is competitive to the other state-of-the-art methods in predicting stock market indices.

A transportation Revitalization index prediction model based on Spatial-Temporal attention mechanism

The global outbreak of COVID-19 has had a substantial impact on various sectors worldwide, including the economy, healthcare, entertainment, policy formulation, and international relations, with the transportation industry being particularly hard-hit. To curb the widespread transmission of the virus, many regions globally have implemented policies and measures to restrict transportation. These actions not only directly affect the transportation industry but also further impose a severe impact on the economy and societal development of various areas. In this context, the Transportation Revitalization Index (TRI) becomes particularly important. It can evaluate the degree of recovery of city traffic conditions after the pandemic, and accurate prediction of TRI can help governments and decision-makers respond more precisely to the challenges that the pandemic brings to the transportation industry. However, existing research primarily focuses on the direct correlation between TRI change data and COVID-19 pandemic data, without fully considering the dynamic spatial correlation features and time dependency features that affect the nonlinear changes of TRI. In light of the above situation, this study proposes a Deep Spatial-Temporal prediction model based on the Attention Mechanism (DeepST-AM). The DeepST-AM deeply integrates historical TRI data with multivariate pandemic information and uses a spatial–temporal attention mechanism to capture the deep and complex spatial–temporal information of urban data. To more accurately capture the long-term complex features of TRI data, this paper designs a Gaussian temporal convolution model dedicated to TRI data. To validate the effectiveness of DeepST-AM, researchers used real data from 29 core cities in China as samples and compared the performance of DeepST-AM with existing multiple methods on TRI prediction tasks. The experimental results showed that compared to other methods, the DeepST-AM proposed in this paper has a significant advantage in the long-term prediction tasks of TRI in terms of performance evaluation, indicator prediction, etc. In summary, this research provides a more accurate and comprehensive prediction model for the traffic recovery status after the pandemic, hoping to provide strong support for future decisions.

Effectiveness of an Artificial Intelligence–Enabled Intervention for Detecting Clinical Deterioration

Inpatient clinical deterioration is associated with substantial morbidity and mortality but may be easily missed by clinicians. Early warning scores have been developed to alert clinicians to patients at high risk of clinical deterioration, but there is limited evidence for their effectiveness. To evaluate the effectiveness of an artificial intelligence deterioration model-enabled intervention to reduce the risk of escalations in care among hospitalized patients using a study design that facilitates stronger causal inference. This cohort study used a regression discontinuity design that controlled for confounding and was based on Epic Deterioration Index (EDI; Epic Systems Corporation) prediction model scores. Compared with other observational research, the regression discontinuity design facilitates causal analysis. Hospitalized adults were included from 4 general internal medicine units in 1 academic hospital from January 17, 2021, through November 16, 2022. An artificial intelligence deterioration model-enabled intervention, consisting of alerts based on an EDI score threshold with an associated collaborative workflow among nurses and physicians. The primary outcome was escalations in care, including rapid response team activation, transfer to the intensive care unit, or cardiopulmonary arrest during hospitalization. During the study, 9938 patients were admitted to 1 of the 4 units, with 963 patients (median [IQR] age, 76.1 [64.2-86.2] years; 498 males [52.3%]) included within the primary regression discontinuity analysis. The median (IQR) Elixhauser Comorbidity Index score in the primary analysis cohort was 10 (0-24). The intervention was associated with a -10.4-percentage point (95% CI, -20.1 to -0.8 percentage points; P = .03) absolute risk reduction in the primary outcome for patients at the EDI score threshold. There was no evidence of a discontinuity in measured confounders at the EDI score threshold. Using a regression discontinuity design, this cohort study found that the implementation of an artificial intelligence deterioration model-enabled intervention was associated with a significantly decreased risk of escalations in care among inpatients. These results provide evidence for the effectiveness of this intervention and support its further expansion and testing in other care settings.

Validation of the Texas Hepatocellular Carcinoma Risk Index Predictive Model for Hepatocellular Carcinoma in Asian Cohort

Hepatocellular carcinoma (HCC) represents a significant global health burden, with its incidence and mortality rates varying significantly across different geographic regions. This variance is largely attributed to differences in the prevalence of risk factors such as hepatitis B and C infections, and alcohol consumption, as well as genetic predispositions that are distinct between Eastern and Western populations. Moreover, the impact of racial and ethnic diversity on the disease's epidemiology further complicates the global understanding and prediction of HCC. Such disparities highlight the critical need to evaluate the applicability of predictive models across diverse populations, acknowledging that a model developed in one region may not necessarily translate with the same accuracy or effectiveness when applied to another, because of these underlying epidemiologic and genetic differences. In this study, we aimed to assess the cross-regional applicability and accuracy of an HCC prediction model (Texas hepatocellular carcinoma risk index [THCC-RI] predictive model) originally developed in Western populations, within an Eastern context.1,2.

Increased risk of colorectal adenomas with metabolic-associated fatty liver disease components

BackgroundMetabolic (dysfunction)-associated fatty liver disease is the most common liver disease related to various metabolic disorders. Colorectal adenomas are related to metabolic dysregulation. Despite the proposed association between non-alcoholic fatty liver disease and colorectal adenomas, the influence of metabolic-associated fatty liver disease on colorectal adenomas has yet to be investigated. Our study investigates the relationship between metabolic-associated fatty liver disease and colorectal adenomas and evaluates the predictive value of fatty liver index for colorectal adenomas. MethodsA retrospective cross-sectional study was conducted on 650 inpatients at Qinghai Provincial People's Hospital. All participants underwent colonoscopy, abdominal ultrasound or CT, relevant laboratory tests, and physical examinations to ascertain baseline characteristics and overall health status. Multivariate logistic regression analysis examined the relationship between metabolic-associated fatty liver disease and colorectal adenomas. Lastly, the ability to identify, accuracy, and clinical applicability of predicting colorectal adenomas through fatty liver index were assessed using receiver operating characteristic curve area under the curve, calibration curve, and decision curve analysis. ResultIn both the colorectal adenomas and control groups, the prevalence of metabolic-associated fatty liver disease was 62.1 % and 35.7 %, respectively. Multivariate analysis indicates that metabolic-associated fatty liver disease was independently correlated with an increased risk of colorectal adenomas (OR, 1.565; 95 % CI, 1.057–2.319; P < 0.05). Further analysis revealed that the risk of colorectal adenomas increased with an increasing quantity of metabolic components in metabolic-associated fatty liver disease (Ptrend < 0.001). The area under the curve of the fatty liver index predictive model was 0.838, with a 95 % CI of 0.807–0.869. The calibration curve indicated excellent agreement, and the decision curve analysis revealed a higher net benefit. ConclusionThe risk of colorectal adenomas was associated with metabolic-associated fatty liver disease, and the risk of developing colorectal adenomas increased with the presence of more metabolic-associated fatty liver disease metabolic components. Furthermore, fatty liver index served as a predictive indicator for screening colorectal adenomas.

A novel air quality index prediction model based on variational mode decomposition and SARIMA-GA-TCN

Due to the rapid development of society and economy, air pollution often occurs. In order to reduce air pollution and improve the accurate prediction of air quality, this paper proposes a seasonal autoregressive comprehensive moving average model combined with the time convolutional network, and uses genetic algorithm and variational mode decomposition to find the parameters of the time convolutional network and reduce the randomness of the sequence. First, the seasonal autoregressive integral moving average model is used to predict the nonlinear information of the time series, and the difference between the original series and the first forecast is decomposed into variational modes, and then used as the prediction target of the time convolutional network. Then, the optimized time convolutional network is used for the second prediction to predict the linear information of the time series. To get the final prediction, add the predictions of the first model and the second model together. The experimental results show that the Root Mean Squared Error, Mean Absolute Percentage Error, Mean Absolute Error and Symmetric Mean Absolute Percentage Error of the model are smaller than those of other relevant prediction models, which proves that the model has the best prediction performance.

A Study on Developing a Model for Predicting the Compression Index of the South Coast Clay of Korea Using Statistical Analysis and Machine Learning Techniques

As large cities are continually being developed around coastal areas, structural damage due to the consolidation settlement of soft ground is becoming more of a problem. Estimating consolidation settlement requires calculating an accurate compressive index through consolidation tests. However, these tests are time-consuming, and there is a risk of the test results becoming compromised while preparing and testing the specimens. Therefore, predicting the compression index based on the results of relatively simple physical property tests enables more reliable and accurate predictions of consolidation settlement by calculating the compression index at multiple points. In this context, this study collected geotechnical data from the soft ground of Korea’s south coast. The collected data were used to construct a dataset for developing a compression index prediction model, and significant influencing factors were identified through Pearson correlation analysis. Simple and multiple linear regression analysis was performed using these factors to derive regression equations, and compression index prediction models were developed by applying machine learning algorithms. The results of deriving the significance of the influencing factors from the developed compression index prediction model showed that natural water content was the most significant factor in predicting the compression index. By collecting a significant amount of high-quality data and using the compression index prediction model and the model construction process proposed in this study, more accurate predictions of the compressive index will be possible in the future.

Research on water environmental indicators prediction method based on EEMD decomposition with CNN-BiLSTM.

Water resources protection is related to the development of the social economy, and the monitoring and prediction of water environmental indicators have important practical significance. In view of the seasonality, periodicity, uncertainty, and nonlinear characteristics of water quality indicators data, traditional prediction models have poor performance. To address this issue, this paper introduces a hybrid water quality index prediction model based on Ensemble Empirical Mode Decomposition (EEMD), combined with Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory Network (BiLSTM). We have conducted out experiments to predict dissolved oxygen based on the water quality monitoring indicators of the Liaohe National Control Sanhongcun Village station in Yichun City. The results show that the model proposed in this paper improves the [Formula: see text] index by 5%, 7% and 5% compared to the suboptimal model in the 4-h, 1-day and 2-day index predictions, respectively.

A Stock Index Prediction Model Based on LSTM: Taking New Energy Vehicles as an Example

Stock indices can partially reflect the overall price level and variations of various stocks in the market. Therefore, analyzing the stock index of new energy vehicles aids in predicting future market trends. However, stock prices, as time series data, display traits of nonlinearity and high noise. This study proposes employing the denoising method of Singular Spectrum Analysis (SSA) on the CNI New Energy Vehicles Index (399417) and constructing an SSA-LSTM model. Comparative results with a single LSTM model demonstrate that the evaluation indicators R2 of the SSA-LSTM model increase by 0.06, RMSE decreases by 54.37, and MAE decreases by 49.49. These findings suggest that SSA can enhance the predictive accuracy of the model.