Traditional Statistical Models Research Articles

Price Prediction of Bitcoin Based on Adaptive Feature Selection and Model Optimization

Bitcoin is one of the most successful cryptocurrencies, and research on price predictions is receiving more attention. To predict Bitcoin price fluctuations better and more effectively, it is necessary to establish a more abundant index system and prediction model with a better prediction effect. In this study, a combined prediction model with twin support vector regression was used as the main model. Twenty-seven factors related to Bitcoin prices were collected. Some of the factors that have the greatest impact on Bitcoin prices were selected by using the XGBoost algorithm and random forest algorithm. The combined prediction model with support vector regression (SVR), least-squares support vector regression (LSSVR), and twin support vector regression (TWSVR) was used to predict the Bitcoin price. Since the model’s hyperparameters have a great impact on prediction accuracy and algorithm performance, we used the whale optimization algorithm (WOA) and particle swarm optimization algorithm (PSO) to optimize the hyperparameters of the model. The experimental results show that the combined model, XGBoost-WOA-TWSVR, has the best prediction effect, and the EVS score of this model is significantly better than that of the traditional statistical model. In addition, our study verifies that twin support vector regression has advantages in both prediction effect and computation speed.

Predicting thalassemia using deep neural network based on red blood cell indices

Background and objectiveThe traditional statistical screening method for thalassemia based on red blood cell (RBC) indices is being replaced by machine learning. Here, we developed deep neural networks (DNNs) that outperformed the traditional method for predicting thalassemia. MethodUsing a dataset of 8693 records comprising genetic tests and other 11 features we constructed 11 DNN models and 4 traditional statistical models and then compared their performances and analysed feature importance for interpreting DNN models. ResultsThe area under the receiver operating characteristic curve, accuracy, Youden’s index, F1 score, sensitivity, specificity, positive predictive value and negative predictive value, were 0.960, 0.897, 0.794, 0.897, 0.883, 0.911, 0.914, and 0.882, respectively, for our best model, and compared with the traditional statistical model based on the mean corpuscular volume, these values were increased by 10.22%, 10.09%, 26.55%, 8.92%, 4.13%, 16.90%, 13.86% and 6.07%, respectively, and by 15.38%, 11.70%, 31.70%, 9.89%, 3.05%, 22.13%, 17.11% and 5.94%, respectively, for the mean cellular haemoglobin model. The DNN model performance will reduce without age, RBC distribution width (RDW), sex, or both WBC and PLT. ConclusionsOur DNN model outperformed the current screening model. In 8 features, RDW and age were the most useful, followed by sex and the combination of WBC and PLT, the remaining nearly useless.

Machine Learning Models Using Routinely Collected Clinical Data Offer Robust and Interpretable Predictions of 90-Day Unplanned Acute Care Use for Cancer Immunotherapy Patients.

Clinical management of patients receiving immune checkpoint inhibitors (ICIs) could be informed using accurate predictive tools to identify patients at risk of short-term acute care utilization (ACU). We used routinely collected data to develop and assess machine learning (ML) algorithms to predict unplanned ACU within 90 days of ICI treatment initiation. We used aggregated electronic health record data from 7,960 patients receiving ICI treatments to train and assess eight ML algorithms. We developed the models using pre-SARS-COV-19 COVID-19 data generated between January 2016 and February 2020. We validated our algorithms using data collected between March 2020 and June 2022 (peri-COVID-19 sample). We assessed performance using area under the receiver operating characteristic curves (AUROC), sensitivity, specificity, and calibration plots. We derived intuitive explanations of predictions using variable importance and Shapley additive explanation analyses. We assessed the marginal performance of ML models compared with that of univariate and multivariate logistic regression (LR) models. Most algorithms significantly outperformed the univariate and multivariate LR models. The extreme gradient boosting trees (XGBT) algorithm demonstrated the best overall performance (AUROC, 0.70; sensitivity, 0.53; specificity, 0.74) on the peri-COVID-19 sample. The algorithm performance was stable across both pre- and peri-COVID-19 samples, as well as ICI regimen and cancer groups. Type of ICI agents, oxygen saturation, diastolic blood pressure, albumin level, platelet count, immature granulocytes, absolute monocyte, chloride level, red cell distribution width, and alcohol intake were the top 10 key predictors used by the XGBT algorithm. Machine learning algorithms trained using routinely collected data outperformed traditional statistical models when predicting 90-day ACU. The XGBT algorithm has the potential to identify high-ACU risk patients and enable preventive interventions to avoid ACU.

A machine learning approach for hierarchical classification of software requirements

Context:Classification of software requirements into different categories is a critically important task in requirements engineering (RE). Developing machine learning (ML) approaches for requirements classification has attracted great interest in the RE community since the 2000s. Objective:This paper aims to address two related problems that have been challenging real-world applications of ML approaches: the problems of class imbalance and high dimensionality with low sample size data (HDLSS). These problems can greatly degrade the classification performance of ML methods. Methods:The paper proposes HC4RC, a novel ML approach for multiclass classification of requirements. HC4RC solves the aforementioned problems through semantic-role based feature selection, dataset decomposition and hierarchical classification. We experimentally compare the effectiveness of HC4RC with three closely related approaches — two of which are based on a traditional statistical classification model whereas one using an advanced deep learning model. Results:Our experiment shows: (1) The class imbalance and HDLSS problems present a challenge to both traditional and advanced ML approaches. (2) The HC4RC approach is simple to use and can effectively address the class imbalance and HDLSS problems compared to similar approaches. Conclusion:This paper makes an important practical contribution to addressing the class imbalance and HDLSS problems in multiclass classification of software requirements.

Toward an improved estimation of flood frequency statistics from simulated flows

AbstractThe estimation of extreme flood frequency for ungauged or poorly gauged catchments is a longstanding problem of great practical importance. Simulated streamflow derived from distributed hydrological models can be used to address this issue, but their representation of extreme flood peaks is often prone to large biases. This study evaluates the potential of a nonasymptotic statistical approach able to consider all the independent flood peaks instead of extremes only, the Simplified Metastatistical Extreme Value (SMEV), for the estimation of extreme flood frequency from time series of simulated streamflow. We examined 28 years of simulated daily streamflow across the contiguous United States and compared SMEV to traditional statistical models based on annual maxima. Our results suggest that when its assumptions are met SMEV can moderate the impact of hydrological model biases in the quantification of extreme flood frequency. SMEV exhibits a lower relative difference between quantiles derived from observations and simulations for all return periods and forcing dataset. Quantiles estimated from simulated streamflow time series (28‐year records) using SMEV are usually in better agreement with the estimates based on 70‐year‐long observations. Geographical variations in the results of SMEV are noticed, with a better performance of SMEV in the east and west coasts (California, New England, and Mid‐Atlantic) and in the southwestern regions (Texas‐Gulf). These results indicate that the potential of SMEV for flood frequency analyses in ungauged and poorly gauged basins deserves further investigations.

Does inclusion of GARCH variance in deep learning models improve financial contagion prediction?

Financial contagions have traditionally been studied using GARCH models to explain the volatility, whereas regression models have been used to predict the stock index values based on different underlying assets. Past research has shown that deep learning regression models have demonstrated superiority over traditional statistical models. This paper creates a hybrid prediction model by using the outputs of GARCH models as an input variable in deep learning regression models. It has been observed that hybrid models provide better results as compared to deep learning models. Such improved prediction shall provide portfolio managers an additional tool to determine the investment strategy.

Hybrid Forecasting for Functional Time Series of Dissolved Oxygen Profiles

Hybridizing machine learning (ML) and traditional statistical modeling is an active area of research, with evidence that integrating the two approaches may improve model performance. In lake ecology, exploring such models is necessary because recent research shows that traditional hydrodynamic models often produce poor short-term forecasts. Thus, in this paper, we compare a selection of hybrid, ML, and statistical models in functional forecasting of dissolved oxygen (DO) profiles in a lake. Functional data have a unique structure wherein the observations are functions, and several ML models for functional data have been recently proposed. The hybrid models in this paper first obtain functional principal components (FPCs) to reduce the dimension, and FPC scores are then forecast using a feed-forward neural network (NN), a recurrent NN, or a random forest (RF). Purely ML NN and RF models forecast each measurement in the functions independently. A functional-statistical model and the persistence model are provided for reference. The forecast performance of these seven models is compared, and prediction bands are built using a subset of the training data to estimate the prediction uncertainty. The RF-based models forecast the best, and the prediction bands of all models provide good average coverage.

Use of an artificial neural network model for estimation of unfrozen water content in frozen soils

The variation of unfrozen water content (UWC) has a significant influence on the physical and mechanical behaviors of frozen soils. Several empirical, semi-empirical, physical, and theoretical models are available in the literature to estimate the UWC in frozen soils. However, these models have limitations due to the complex interactions of various influencing factors that are not well understood or fully established. For this reason, in the present study, an artificial neural network (ANN) modeling framework is proposed and the PyTorch package is used for predicting UWC. Extensive UWC data of various types of soils tested under various conditions were collected through an extensive search of the literature. The developed ANN model showed good performance for the testing dataset. Its performance was further compared with two traditional statistical models on four soils and found to outperform these traditional models. Detailed discussions on the developed ANN model, and its strengths and limitations in comparison to different other models are provided. The study demonstrates that the proposed ANN model is simple yet reliable for estimating the UWC of various soils. In addition, the summarized UWC data and the proposed machine learning modeling framework are valuable for future studies related to frozen soils.

Bearing performance degradation assessment and remaining useful life prediction based on data-driven and physical model

Intelligent health maintenance of bearings usually consists of two stages: constructing effective health assessment indicators and accurate remaining useful life prediction models. However, many prediction models are available only when many constraints are met, and the health assessment indicators may not be able to accurately track the performance degradation process of bearings. This study proposes a bearing performance degradation assessment and remaining life prediction method. First, the health evaluation index family (referred to as the generalized high-order moment coefficient) was constructed based on the generalized power mean and high-order origin moments for health assessment. Subsequently, an improved Paris–Erdogan model is proposed, which uses the optimal health evaluation index as input to predict the remaining life of the bearing after the initial failure. The experimental results show that the proposed method has a higher performance degradation tracking accuracy and a smaller prediction error than the combination of traditional statistical indicators and prediction models.

Exploring predictors of welfare dependency 1, 3, and 5 years after mental health-related absence in danish municipalities between 2010 and 2012 using flexible machine learning modelling

BackgroundUsing XGBoost (XGB), this study demonstrates how flexible machine learning modelling can complement traditional statistical modelling (multinomial logistic regression) as a sensitivity analysis and predictive modelling tool in occupational health research.DesignThe study predicts welfare dependency for a cohort at 1, 3, and 5 years of follow-up using XGB and multinomial logistic regression (MLR). The models’ predictive ability is evaluated using tenfold cross-validation (internal validation) and geographical validation (semi-external validation). In addition, we calculate and graphically assess Shapley additive explanation (SHAP) values from the XGB model to examine deviation from linearity assumptions, including interactions. The study population consists of all 20–54 years old on long-term sickness absence leave due to self-reported common mental disorders (CMD) between April 26, 2010, and September 2012 in 21 (of 98) Danish municipalities that participated in the Danish Return to Work program. The total sample of 19.664 observations is split geospatially into a development set (n = 9.756) and a test set (n = 9.908).ResultsThere were no practical differences in the XGB and MLR models’ predictive ability. Industry, job skills, citizenship, unemployment insurance, gender, and period had limited importance in predicting welfare dependency in both models. On the other hand, welfare dependency history and reason for sickness absence were strong predictors. Graphical SHAP-analysis of the XGB model did not indicate substantial deviations from linearity assumptions implied by the multinomial regression model.ConclusionFlexible machine learning models like XGB can supplement traditional statistical methods like multinomial logistic regression in occupational health research by providing a benchmark for predictive performance and traditional statistical models' ability to capture important associations for a given set of predictors as well as potential violations of linearity.Trial registrationISRCTN43004323.

Long-term care insurance purchase decisions of registered nurses: Deep learning versus logistic regression models

ObjectiveThe purpose of this study was to use a deep learning model and a traditional statistical regression model to predict the long-term care insurance decisions of registered nurses. MethodsWe Prospectively surveyed 1,373 registered nurses with a minimum of 2 years of full-time working experience at a large medical center in Taiwan: 615 who already owned long-term care insurance (LTCI), 332 who had no intention to purchase LTCI (group 1), and 426 who intended to purchase LTCI (group 2). ResultsAfter inverse probability of treatment weighting (IPTW), no statistically significant differences were identified in the study characteristics of the two groups. All the performance indices for the deep neural network (DNN) model were significantly higher than those of the multiple logistic regression (MLR) model (P<0.001). The strongest predictor of an individual's long-term care insurance decision was their risk propensity score, followed by their caregiving responsibilities, whether they live with older adult relatives, their experiences of catastrophic illness, and their openness to experience. ConclusionsThe DNN model is useful for predicting long-term care insurance decisions. Its prediction accuracy can be increased through training with temporal data collected from registered nurses. Future research can explore designs for two-level or multilevel models that explain the contextual effects of the risk factors on long-term care insurance decisions.

A comparison of machine learning algorithms and traditional regression-based statistical modeling for predicting hypertension incidence in a Canadian population

Risk prediction models are frequently used to identify individuals at risk of developing hypertension. This study evaluates different machine learning algorithms and compares their predictive performance with the conventional Cox proportional hazards (PH) model to predict hypertension incidence using survival data. This study analyzed 18,322 participants on 24 candidate features from the large Alberta’s Tomorrow Project (ATP) to develop different prediction models. To select the top features, we applied five feature selection methods, including two filter-based: a univariate Cox p-value and C-index; two embedded-based: random survival forest and least absolute shrinkage and selection operator (Lasso); and one constraint-based: the statistically equivalent signature (SES). Five machine learning algorithms were developed to predict hypertension incidence: penalized regression Ridge, Lasso, Elastic Net (EN), random survival forest (RSF), and gradient boosting (GB), along with the conventional Cox PH model. The predictive performance of the models was assessed using C-index. The performance of machine learning algorithms was observed, similar to the conventional Cox PH model. Average C-indexes were 0.78, 0.78, 0.78, 0.76, 0.76, and 0.77 for Ridge, Lasso, EN, RSF, GB and Cox PH, respectively. Important features associated with each model were also presented. Our study findings demonstrate little predictive performance difference between machine learning algorithms and the conventional Cox PH regression model in predicting hypertension incidence. In a moderate dataset with a reasonable number of features, conventional regression-based models perform similar to machine learning algorithms with good predictive accuracy.

Predicting incident dementia in cerebral small vessel disease: comparison of machine learning and traditional statistical models

BackgroundCerebral small vessel disease (SVD) contributes to 45% of dementia cases worldwide, yet we lack a reliable model for predicting dementia in SVD. Past attempts largely relied on traditional statistical approaches. Here, we investigated whether machine learning (ML) methods improved prediction of incident dementia in SVD from baseline SVD-related features over traditional statistical methods. MethodsWe included three cohorts with varying SVD severity (RUN DMC, n = 503; SCANS, n = 121; HARMONISATION, n = 265). Baseline demographics, vascular risk factors, cognitive scores, and magnetic resonance imaging (MRI) features of SVD were used for prediction. We conducted both survival analysis and classification analysis predicting 3-year dementia risk. For each analysis, several ML methods were evaluated against standard Cox or logistic regression. Finally, we compared the feature importance ranked by different models. ResultsWe included 789 participants without missing data in the survival analysis, amongst whom 108 (13.7%) developed dementia during a median follow-up of 5.4 years. Excluding those censored before three years, we included 750 participants in the classification analysis, amongst whom 48 (6.4%) developed dementia by year 3. Comparing statistical and ML models, only regularised Cox/logistic regression outperformed their statistical counterparts overall, but not significantly so in survival analysis. Baseline cognition was highly predictive, and global cognition was the most important feature. ConclusionsWhen using baseline SVD-related features to predict dementia in SVD, the ML survival or classification models we evaluated brought little improvement over traditional statistical approaches. The benefits of ML should be evaluated with caution, especially given limited sample size and features.

OPTIMIZATION OF QUANTITATIVE RESEARCH METHODS IN SOCIAL SCIENCES IN THE ERA OF BIG DATA

As information technology continues to advance, the complexity of data is ever-increasing. Traditional quantitative research methods in the social sciences, such as basic visualization and traditional statistical models, are gradually becoming inadequate in meeting the demands of modern data analysis. Despite the challenges that big data presents, it also brings new opportunities – through its usage, the optimization of traditional methods can be achieved. More intricate graphing techniques such as mosaic plots, alluvial plots, slope charts, and area charts, alongside machine learning algorithms that are better adapted for big data analysis such as decision trees, random forests, and K-Means algorithm, are opening new avenues for quantitative analysis in social sciences. This will ultimately foster further development of the field by allowing new methods and ideas to emerge.

Research on obstacle climbing gait structure design and gait control of hexapod wall climbing robot based on STM32F103 core controller

The hexapod wall climbing robots have the advantages of traversing complex wall surfaces. To traverse complex environments autonomously, it must possess the capability to select gait parameters and paths appropriate for the wall surface. Path planning and gait optimization is a fundamental issue in the aspect of stable, energy efficient robot navigation in complex environments with static and dynamic obstacles. Traditional statistical models have been developed to get the optimal path and gait parameters but the result obtained was very poor. Metaheuristic algorithms are gaining importance in robotic gait planning. In this paper, we proposed robust two stage gait planning approach for predicting collision-free, distance-minimal, smooth navigation path and ensuring stable, energy efficient gait patterns for robots using hybrid metaheuristic algorithms. In the first stage, optimal climbing path for robot is predicted using Tri-objective Grey Wolf Path Optimization (TGWPO) based on obstacle and target detection. In the second stage, the gait parameters adaptive to the constructed climbing path are optimized using Adaptive multi-objective Particle swarm optimization (AMPSO). The hexapod wall climbing robot is designed with STM32F103 as core controller modeled with optimal path planner (using TDWPO) and gait optimizer module (using AMPSO). STM32F103 controller commands and controls the robot to climb on wall with optimized gait parameters according to the optimal path. We analyzed the efficacy of the proposed two stage gait planning approach using TDWPO-AMPSO for hexapod wall climbing robots with existing gait planning approaches in terms of path length, climbing time, gait stability, obstacle avoidance, and energy efficiency. The result analysis showed that the suggested gait planning approach is efficient over conventional strategies for climbing robots.

A Learning-based Correlated Graph Model for Spinal Cord Injury Prediction from Magnetic Resonance Spinal Images

In epidemiological research on spine surgery, machine learning represents a promising new area. It is made up of several algorithms that work together to identify patterns in the data. Machine learning provides many benefits over traditional regression techniques, including a lower necessity for a priori predictor information and a higher capacity for managing huge datasets. Recent research has made significant progress toward using machine learning more effectively in spinal cord injury (SCI). Machine learning algorithms are employed to analyze non-traumatic and traumatic spinal cord injuries. Non-traumatic spinal cord injuries often reflect degenerative spine conditions that cause spinal cord compression, such as degenerative cervical myelopathy. This article proposes a novel correlated graph model (CGM) that adopts correlated learning to predict various outcomes published in traumatic and non-traumatic SCI. In the studies mentioned, machine learning is used for several purposes, including imaging analysis and epidemiological data set prediction. We discuss how these clinical predictive models are based on machine learning compared to traditional statistical prediction models. Finally, we outline the actions that must be taken in the future for machine learning to be a more prevalent statistical analysis method in SCI.

A spatio-temporal deep learning model for short-term bike-sharing demand prediction

&lt;abstract&gt; &lt;p&gt;Bike-sharing systems are widely operated in many cities as green transportation means to solve the last mile problem and reduce traffic congestion. One of the critical challenges in operating high-quality bike-sharing systems is rebalancing bike stations from being full or empty. However, the complex characteristics of spatiotemporal dependency on usage demand may lead to difficulties for traditional statistical models in dealing with this complex relationship. To address this issue, we propose a graph-based neural network model to learn the representation of bike-sharing demand spatial-temporal graph. The model has the ability to use graph-structured data and takes both spatial- and temporal aspects into consideration. A case study about bike-sharing systems in Nanjing, a large city in China, is conducted based on the proposed method. The results show that the algorithm can predict short-term bike demand with relatively high accuracy and low computing time. The predicted errors for the hourly station level usage demand prediction are often within 20 bikes. The results provide helpful tools for short-term usage demand prediction of bike-sharing systems and other similar shared mobility systems.&lt;/p&gt; &lt;/abstract&gt;

Application Of Machine Learning Algorithms to Free Cash Flows Growth Rate Estimation

Machine learning (ML) demonstrates superior accuracy in financial time-series forecasting compared to traditional statistical models. While most studies focus on applying ML algorithms to high-frequency pricing data, the availability of fundamental financial data is limited as it is generated quarterly. This paper investigates the performance of nine ML algorithms in small sample data sets, against an ARIMA model — frequently used for financial time-series forecasting — serving as a benchmark. Results obtained from 100 US companies indicate that the majority of ML algorithms exhibit low error rates on the test set, outperforming benchmark results. Notably, the k-nearest neighbor algorithm achieves the highest prediction accuracy among the algorithms considered, even with only 33 data observations, while avoiding overfitting.

Predicting safety performance on motorways during the pandemic based on geometric design: A case study in Portugal

The mobility restrictions due to the covid-19 pandemic have created an unprecedented situation in the road system. Declared lockdowns have significantly altered the traffic volumes and perhaps also driver behavior. This study conducts research on crashes occurred on motorway A29 in Portugal before and during the disrupted mobility context. Safety performance functions were adjusted with negative binomial distribution. The segmentation was based on horizontal alignments. 5 of the 27 variables initially considered were found to be significant; namely traffic volume, segment length, curvature change rate, presence of deceleration lane and year. The quality of the fitted models was verified using cumulative residuals plots. The results showed that a traditional statistical modelling approach explains accident occurrence in a similar way before and during the pandemic.

Machine Learning Models for Statistical Analysis

Compared to traditional statistical models, Machine Learning (ML) algorithms provide the ability to interpret, understand and summarize patterns and regularities in observed data for making predictions in an advanced and more sophisticated way. The main reasons for the advantage of ML methods in making predictions are a small number of significant predictors of the statistical models, which means limited informative capability, and pseudo-correct regular statistical patterns, used without previous understanding of the used data causality. Also, some ML methods, like Artificial Neural Networks, use non-linear algorithms, considering links and associations between parameters. On the other hand, statistical models use one-step-ahead linear processes to improve only short-term prediction accuracy by minimizing a cost function. Although designing an optimal ML model can be a very complex process, it can be used as a potential solution for making improved prediction models compared to statistical ones. However, ML models will not automatically improve prediction accuracy, so it is necessary to evaluate and analyze several statistical and ML methods, including some artificial neural networks, through accuracy measures for prediction purposes in various fields of applications. A couple of techniques for improving suggested ML methods and artificial neural networks are proposed to get better accuracy results