Construction Of Predictive Models Research Articles

DelayDetect: Pre-takeoff Delay Anticipation

Abstract: Flight delays pose significant challenges to both passengers and airlines, leading to inconvenience, financial losses, and operational disruptions. A comprehensive system is introduced to address the issue of airline flight delays through the application of machine learning models. Leveraging comprehensive datasets encompassing historical flight records, meteorological data, airport congestion patterns and other variables, this model aims to construct predictive models capable of accurately forecasting the probability of flight delays. Various machine learning methodologies including random forests and regression models, are systematically examined in this predictive task. Performance evaluation is conducted employing established metrics such as accuracy and precision. In conclusion, flight delay anticipation is a valuable tool that can revolutionize the aviation industry by minimizing disruptions, reducing costs, and increasing passenger satisfaction.

Development and validation of a prediction model for suboptimal ovarian response in polycystic ovary syndrome (PCOS) patients undergoing GnRH-antagonist protocol in IVF/ICSI cycles

BackgroundPCOS patients with unexpectedly low oocyte yield following conventional ovarian stimulation are referred to as suboptimal responders. However, identifying suboptimal responders presents a significant challenge within reproductive medicine and limited research exists on the occurrence of suboptimal response. This analysis aimed to develop a predictive model of suboptimal response during in vitro fertilization/intracytoplasmic sperm injection (IVF/ICSI) treatments in PCOS patients.MethodsThis retrospective study involved a cohort of 313 PCOS patients undergoing their first IVF/ICSI cycle from 2019 to 2022. Univariate logistic regression analyses, least absolute shrinkage, selection operator regression analysis, and recursive feature elimination were employed to identify relevant characteristics and construct predictive models. Moreover, a nomogram was constructed based on the best model. Receiver operating characteristic curves, decision curve analysis (DCA), and calibration curves were used to evaluate the model.ResultsThe predictors included in the model were age, Anti-Mullerian hormone, antral follicle count, and basal follicle-stimulating hormone. The area under the receiver operating characteristic curve (AUC) was 0.7702 (95% confidence interval 0.7157–0.8191). The AUC, along with the DCA curve and calibration curve, demonstrated a satisfactory level of congruence and discrimination ability.ConclusionThe nomogram effectively predicted the probability of suboptimal response in PCOS patients undergoing gonadotropin-releasing hormone antagonist protocol during IVF/ICSI treatment.

Monitoring Land Management Practices Using Vis–NIR Spectroscopy Provides Insights into Predicting Soil Organic Carbon and Limestone Levels in Agricultural Plots

This study aimed to establish sound relationships between soil properties of agricultural land in central Spain and their spectral attributes to contribute to deriving an indicator for sustainable farm management. Sixteen plots, managed under various conditions, eight with traditional tillage and eight with other alternative managements, were selected to gather soil samples representing three predominant soil orders (Leptosols, Cambisols, and Luvisols). Soil sampling was conducted from depths ranging from 0 to 30 cm (0–50; 5–10, 10–20, and 20–30 cm), ensuring a broad spectrum of sample variability across different times and locations. The reflectance of soil 64 soil samples was measured within the range of 400 to 900 nm, and the corresponding concentrations of soil organic carbon and majoritarian minerals, calcium carbonate, quartz, phyllosilicates, K-Feldspar, and plagioclase were determined for each sample. Partial least squares analysis was employed to construct prediction models using a calibration dataset comprising 66% of randomly selected samples. The remaining 33% of samples were utilized for model validation. The prediction models for the measured soil chemical properties yielded R2 values ranging from 0.14 to 0.79. Only SOC and limestone provided accurate prediction models. These findings hold promise for developing a soil health indicator tailored for site-specific crop management. However, the complex composition of soil organic carbon and calcium carbonate in certain soils underscores the importance of careful interpretation and validation of remote sensing data, as well as the need for advanced modeling approaches that can account for the interactions between multiple soil constituents.

Analysis of Shield Tunneling Parameters and Research on Prediction Model of Tunneling Excavation Speed in Volcanic Ash Strata of Jakarta–Bandung High-Speed Railway Project

Insufficient investigations have been conducted on the analysis of shield tunneling parameters and the prediction of the tunneling excavation speed in formations composed of volcanic ash strata. To address this issue, we employ a comprehensive approach utilizing literature research, mathematical statistics, and other methodologies, centered on the analysis of the No. 1 Tunnel of the Jakarta–Bandung High-Speed Railway. Our focus is on examining the evolution patterns and inter-relationships of shield tunneling parameters within volcanic ash strata. Subsequently, we propose an optimized strategy for these tunneling parameters. By employing six machine-learning algorithms to construct prediction models, we compare and analyze their performance in predicting the tunneling excavation speed. The results indicate a positive correlation between slurry pressure and tunnel depth in volcanic ash strata, suggesting that the grouting pressure should exceed the slurry pressure by approximately 0.22 MPa. In the composite stratum of “volcanic ash debris + round gravel”, the cutter torque exhibits a strong negative correlation with the total thrust (−0.77). Due to tool wear and ground resistance, the excavation speed and cutter speed are weakly negatively correlated. Compared to other strata, shield tunneling in volcanic ash strata exhibits larger grouting pressure fluctuations, slower tunneling excavation speed, greater total thrust, higher cutter torque, and lower cutter speed. Regarding shield tunneling excavation speed prediction, the ranking of the algorithm performance is RF > DNN > ANN > BPNN > MNR > SVM, with RF achieving a decision coefficient of 0.829. The RF model is well-suited for predicting the shield structure tunneling excavation speed.

Using Image Analysis Technique for Predicting Light Lamb Carcass Composition

Over the years, numerous techniques have been explored to assess the composition and quality of sheep carcasses. This study focuses on the utilization of video image analysis (VIA) to evaluate the composition of light lamb carcasses (4.52 ± 1.34 kg, mean cold carcass weight ± SD). Photographic images capturing the lateral and dorsal sides of fifty-five light lamb carcasses were subjected to analysis. A comprehensive set of measurements was recorded, encompassing dimensions such as lengths, widths, angles, areas, and perimeters, totaling 21 measurements for the lateral view images and 29 for the dorsal view images. K-Folds stepwise multiple regression analyses were employed to construct prediction models for carcass tissue weights (including muscle, subcutaneous fat, intermuscular fat, and bone) and their respective percentages. The most effective prediction equations were established using data from cold carcass weight (CCW) and measurements from both dorsal and lateral views. These models accounted for a substantial portion of the observed variation in the weights of all carcass tissues (with K-fold-R2 ranging from 0.83 to 0.98). In terms of carcass tissue percentages, although the degree of variation explained was slightly lower (with K-fold-R2 ranging from 0.41 to 0.78), the VIA measurements remained integral to the predictive models. These findings underscore the efficacy of VIA as an objective tool for assessing the composition of light lamb carcasses, which are carcasses weighing ≈ 4–8 kg.

A combinatorial MRI sequence-based radiomics model for preoperative prediction of microsatellite instability status in rectal cancer

This study aimed to develop an optimal radiomics model for preoperatively predicting microsatellite instability (MSI) in patients with rectal cancer (RC) based on multiparametric magnetic resonance imaging. The retrospective study included 308 RC patients who did not receive preoperative antitumor therapy, among whom 51 had MSI. Radiomics features were extracted and dimensionally reduced from T2-weighted imaging (T2WI), T1-weighted imaging (T1WI), diffusion-weighted imaging (DWI), and T1-weighted contrast enhanced (T1CE) images for each patient, and the features of each sequence were combined. Multifactor logistic regression was used to screen the optimal feature set for each combination. Different machine learning methods were applied to construct predictive MSI status models. Relative standard deviation values were determined to evaluate model performance and select the optimal model. Receiver operating characteristic (ROC) curve, calibration curve, and decision curve analyses were performed to evaluate model performance. The model constructed using the k-nearest neighbor (KNN) method combined with T2WI and T1CE images performed best. The area under the curve values for prediction of MSI with this model were 0.849 (0.804–0.887), with a sensitivity of 0.784 and specificity of 0.805. The Delong test showed no significant difference in diagnostic efficacy between the KNN-derived model and the traditional logistic regression model constructed using T1WI + DWI + T1CE and T2WI + T1WI + DWI + T1CE data (P > 0.05) and the diagnostic efficiency of the KNN-derived model was slightly better than that of the traditional model. From ROC curve analysis, the KNN-derived model significantly distinguished patients at low- and high-risk of MSI with the optimal threshold of 0.2, supporting the clinical applicability of the model. The model constructed using the KNN method can be applied to noninvasively predict MSI status in RC patients before surgery based on radiomics features from T2WI and T1CE images. Thus, this method may provide a convenient and practical tool for formulating treatment strategies and optimizing individual clinical decision-making for patients with RC.

#1665 Mechanisms underlying long-term weight changes and their impact on all-cause mortality among chronic hemodialysis patients

Abstract Background and Aims Observational studies have demonstrated a significant association between long-term weight loss and weight gain and an increased risk of mortality among chronic hemodialysis patients. However, underlying mechanisms of these associations remain insufficiently explored. To address this knowledge gap, we conducted an in-depth analysis using a cohort of hemodialysis patients, benefiting from comprehensive baseline data, regular six-month evaluations, and an extended follow-up period. We employed advanced statistical techniques, including Lasso regression, to construct predictive models for long-term weight loss and gain. Furthermore, we conducted mediation analyses to elucidate whether weight change mediates the impact of major risk factors on all-cause mortality. Method This post-hoc analysis utilized data from participants in a previous randomized controlled trial conducted between 2006 and 2011, named as the Olmesartan clinical trial in Okinawan patients under the OKIDS (OCTOPUS) study. Subsequently, we tracked participants' mortality outcomes until July 2018. At the time of enrollment, we collected comprehensive baseline information, encompassing demographics, medical history, and laboratory data. Throughout the trial, participants' body weights were meticulously recorded every six months. Our analysis was restricted to patients who survived for at least two years post-enrollment, ensuring a minimum of five body weight measurements during the trial. Lasso regression was employed in training datasets (comprising 60% of participants) to identify crucial risk factors associated with long-term weight gain (>1 kg per year) or weight loss (<−1 kg per year) among chronic hemodialysis patients. These selected models were subsequently applied to paired validation datasets (comprising 40% of participants), and receiver operating characteristic (ROC) curves were used to calculate the area under the curve (AUC), aiding in the identification of key risk factors for long-term weight changes. Subsequently, we conducted mediation analyses to investigate whether weight change mediated the relationship between risk factors and all-cause mortality. Results Our analysis included 404 out of 461 OCTOPUS participants, with 60.9% being male, a mean age of 59.2 years (±11.7), and a mortality rate of 41.6%. The median follow-up period extended to 10.3 years. In the training datasets, Lasso models identified critical predictors for weight increase, including a history of diabetes, younger age, normal cardio-thoracic ratio (CTR) (<50% for males and <53% for females), and BMI <20. Conversely, predictors for weight decrease included BMI ≥20, serum sodium <135 mEq/L, serum albumin <3.5 g/dL, and older age. Weight increase demonstrated higher predictability (mean AUC of 0.59) compared to weight decrease (mean AUC of 0.55) in the validation datasets. Mediation analyses revealed that weight loss mediated 30% of the impact of older age (≥70 years old) on all-cause mortality (P = 0.068). Conclusion Our findings suggest that, among chronic hemodialysis patients, long-term weight increase is associated with a history of diabetes and younger age, while long-term weight loss is linked to BMI (≥20), hyponatremia, hypoalbuminemia, and older age. Notably, long-term weight loss appears to explain 30% of the increased risk of all-cause mortality associated with older age (≥70 years old).

Identification of a novel matrix metalloproteinases-related prognostic signature in hepatocellular carcinoma.

Hepatocellular carcinoma (HCC) is the most common primary liver cancer worldwide. Cancer cells' local infiltration, proliferation, and spread are mainly influenced by the protein hydrolyzing function of different matrix metalloproteinases (MMPs). However, no study has determined the relationship between MMPs and prognostic prediction in HCC. Expression profiles of mRNA and MMPs-related genes were obtained from publicly available databases. Cox regression and LASSO Cox regression analysis were used to identify and predict MMPs-related prognostic signature and construct predictive models for overall survival (OS). A nomogram was used to validate the accuracy of the prediction model. Drug prediction was performed using the Genomics of Drug Sensitivity in Cancer (GDSC) dataset, and single-cell clustering analysis was performed to further understand the significance of the MMPs-related signature. A MMPs-related prognostic signature (including RNPEPL1, ADAM15, ADAM18, ADAMTS5, CAD, YME1L1, AMZ2, PSMD14, and COPS6) was identified. Using the median value, HCC patients in the high-risk group showed worse OS than those in the low-risk group. Immune microenvironment analysis showed that patients in the high-risk group had higher levels of M0 and M2 macrophages. Drug sensitivity analysis revealed that the IC50 values of sorafenib, cisplatin, and cytarabine were higher in the high-risk group. Finally, the single-cell cluster analysis results showed that YME1L1 and COPS6 were the major genes expressed in the monocyte cluster. A novel MMPs-related signature can be used to predict the prognosis of HCC. The findings of this research could potentially impact the predictability of the prognosis and treatment of HCC.

Analyzing polycyclic aromatic hydrocarbons using topological indices and QSPR analysis to reveal molecular complexity

Polycyclic aromatic hydrocarbons (PAHs) have distinctive chemical structures and are well known for their wide range of uses and environmental relevance. This work explores the impact of these structural characteristics on eccentricity-based topological indices offering information about the arrangement of atoms within the molecules. This study uses quantitative structure-property relationship (QSPR) analysis to construct prediction models for understanding and forecasting specific PAHs including Dibenzo[e,l]Pyrene, Heptacence, Heptaphene, Naphthacene, Naphthalene, Naphto[1,2a]pyrene, Naphtho[2,3a]pyrene, perylene, Perylene, Picene, Phenanthrene, Pyrene, Tetraphene, Tribenzo[b,n,pqr]perylene, Tribenzo[a,fg,op]tetracene and Triphenylene. Furthermore, regression analysis applies to clarify the quantitative correlations between the factors under study and improves the interpretability of the data produced. The combined use of these diverse approaches advances a thorough comprehension of the mutual influence of chemical structure, topological indices and predictive modeling about PAHs.

Machine learning-based prediction models affecting the recovery of postoperative bowel function for patients undergoing colorectal surgeries

PurposeThe debate surrounding factors influencing postoperative flatus and defecation in patients undergoing colorectal resection prompted this study. Our objective was to identify independent risk factors and develop prediction models for postoperative bowel function in patients undergoing colorectal surgeries.MethodsA retrospective analysis of medical records was conducted for patients who undergoing colorectal surgeries at Peking University People’s Hospital from January 2015 to October 2021. Machine learning algorithms were employed to identify risk factors and construct prediction models for the time of the first postoperative flatus and defecation. The prediction models were evaluated using sensitivity, specificity, the Youden index, and the area under the receiver operating characteristic curve (AUC) through logistic regression, random forest, Naïve Bayes, and extreme gradient boosting algorithms.ResultsThe study included 1358 patients for postoperative flatus timing analysis and 1430 patients for postoperative defecation timing analysis between January 2015 and December 2020 as part of the training phase. Additionally, a validation set comprised 200 patients who undergoing colorectal surgeries from January to October 2021. The logistic regression prediction model exhibited the highest AUC (0.78) for predicting the timing of the first postoperative flatus. Identified independent risk factors influencing the time of first postoperative flatus were Age (p < 0.01), oral laxatives for bowel preparation (p = 0.01), probiotics (p = 0.02), oral antibiotics for bowel preparation (p = 0.02), duration of operation (p = 0.02), postoperative fortified antibiotics (p = 0.02), and time of first postoperative feeding (p < 0.01). Furthermore, logistic regression achieved an AUC of 0.72 for predicting the time of first postoperative defecation, with age (p < 0.01), oral antibiotics for bowel preparation (p = 0.01), probiotics (p = 0.01), and time of first postoperative feeding (p < 0.01) identified as independent risk factors.ConclusionsThe study suggests that he use of probiotics and early recovery of diet may enhance the recovery of bowel function in patients undergoing colorectal surgeries. Among the various analytical methods used, logistic regression emerged as the most effective approach for predicting the timing of the first postoperative flatus and defecation in this patient population.

Deployment of a Phenotypic Characterization System for Effective Identification of the Onset of Asthma Disease

Background Essentially, machine learning techniques help with clinical decision-making by forecasting prediction results based on recent and historical data, which are frequently found in carefully chosen clinical data repositories. In order to uncover hidden patterns in the data, machine learning applies sophisticated analytical techniques that conduct an exploratory analysis while constructing prediction models to support clinical judgment. Objective To effectively identify asthmatics in two distinct cohorts representing India's rural and urban populations by adopting a phenotypic characterization approach. Methods Cross-sectional and categorical in design, the data represent the two populations, with clinical history information emphasizing clinical symptoms and patterns defining the condition. The method adopts a hybrid approach since it uniquely blends the unsupervised and supervised learning techniques to explore the advantages of both. The clustering data emphasizing the phenotypic characteristics of asthma is input to the classifier, and the performance of the classifier was continuously monitored for significant improvement in the results. Results Asthma disease outcome predictions made by the hybrid decision support system were quite accurate, with classification accuracy reaching up to 85.1% and 95.3% for the two datasets, respectively. Conclusion Since asthma is a heterogeneous disease with multiple subtypes, employing clustering information in the form of cluster evaluation scores as an input parameter to the classifiers can effectively predict disease outcomes.

Advances in the construction of risk prediction models for chronic kidney failure

Chronic kidney disease (CKD) is a major public health problem worldwide. When CKD patients progress to the stage of kidney failure, kidney replacement therapy (KRT) or conservative treatment (palliative or non-dialysis treatment) will be needed. The risk prediction models of chronic kidney failure have been developed in recent years. These models, focusing on demographic indicators, clinical indicators, and laboratory data, are used to predict the likelihood of progression to kidney failure and requiring KRT. This article will retrieve prediction models for chronic kidney failure as an outcome, demonstrate the current research progress, and hope that it may be helpful for the strategies of preventing chronic kidney failure.

Whole-orbit-based multiparametric assessment of disease activity of thyroid eye disease on Dixon MRI.

This study aimed to explore the diagnostic value of whole-orbit-based multiparametric assessment on Dixon MRI for the evaluation of the thyroid eye disease (TED) activity. The retrospective study enrolled patients diagnosed as TED and obtained their axial and coronal Dixon MRI scans. Multiparameters were assessed, including water fraction (WF), fat fraction (FF) of extraocular muscles (EOMs), orbital fat (OF), and lacrimal gland (LG). The thickness of OF and herniation of LG were also measured. Univariable and multivariable logistic regression was applied to construct prediction models based on single or multiple structures. Receiver operating characteristic (ROC) curve analysis was also implemented. Univariable logistic analysis revealed significant differences in water fraction (WF) of the superior rectus (P = 0.018), fat fraction (FF) of the medial rectus (P = 0.029), WF of OF (P = 0.004), and herniation of LG (P = 0.012) between the active and inactive TED phases. Multivariable logistic analysis and corresponding receiver operating characteristic curve (ROC) analysis of each structure attained the area under the curve (AUC) values of 0.774, 0.771, and 0.729 for EOMs, OF, and LG, respectively, while the combination of the four imaging parameters generated a final AUC of 0.909. Dixon MRI may be used for fine multiparametric assessment of multiple orbital structures. The whole-orbit-based model improves the diagnostic performance of TED activity evaluation.

Predictive value of PD-L1 and TMB for short-term efficacy prognosis in non-small cell lung cancer and construction of prediction models.

To investigate the correlation between programmed death ligand 1(PD-L1), tumor mutation burden (TMB) and the short-term efficacy and clinical characteristics of anti-PD-1 immune checkpoint inhibitor combination chemotherapy in NSCLC patients. The efficacy of the prediction model was evaluated. A total of 220 NSCLC patients receiving first-line treatment with anti-PD-1 immune checkpoint inhibitor combined with chemotherapy were retrospectively collected. The primary endpoint was short-term efficacy ORR. The correlation between short-term efficacy, PD-L1, TMB, and clinical characteristics using χ2 test or t-test was evaluated. Screen the independent prognostic factors using univariate and multivariate logistic regression analyses, and construct a nomogram prediction model using the "rms" package in R software. Using receiver operating characteristic (ROC) curve analysis to evaluate the independent Prognostic factors and the prediction model. Using decision curve analysis (DCA) to verify the superiority of the prediction model. The mean values of PD-L1, TMB, neutrophils, lymphocytes, neutrophil-to-lymphocyte ratio, and albumin were the highest in the ORR group, PD-L1 expression and TMB correlated with epidermal growth factor receptor expression. Multivariate analyses showed that PD-L1, TMB, and neutrophil were independent prognostic factors for ORR. The area under the ROC curve (AUC) values of the ROC constructed based on these three indicators were 0.7104, 0.7139, and 0.7131, respectively. The AUC value under the ROC of the nomogram model was 0.813. The DCA of the model showed that all three indicators used together to build the prediction model of the net return were higher than those of the single indicator prediction model. PD-L1, TMB, and neutrophils are independent prognostic factors for short-term efficacy. The nomogram prediction model constructed using these three indicators can further improve predictive efficacy of ICIs in patients with NSCLC.

Predicting Accident Severity using Machine Learning

Each year, millions of people are killed in automobile accidents. Predicting the severity of an occurrence allows local authorities to respond quickly and save many lives. Information and data on traffic accidents made available by public organizations can be used to categories these incidents based on their nature and severity, and then attempt to construct predictive models that can be further investigated to identify fatal accident risk factors. The study provides ways to develop a system for determining the severity of accidents. To evaluate the severity of the collision, we use a variety of weather-related characteristics such as temperature, humidity, visibility, and pressure, as well as several other circumstances, such as the presence of a traffic light or a junction. The Select-K-Best features selection algorithms were used to choose the best characteristics from a list of 47. The accuracy of both balanced and unbalanced data was measured, and the balanced data was chosen for further analysis. The balanced dataset is then trained, analyzed, and compared with a number of machine learning approaches, including the Random Forest Classifier (RFC), K closest neighbour (KNN) classifier, and Naive Bayes classifier. The RFC classifier outperformed with an AUC of 95%, whereas the naïve bayes underperformed. Furthermore, the accuracy is improved by using all of the aforementioned methods as base learners for stacking ensemble models with logistic regression as meta learner. This stacking ensemble strategy outperforms RFC with improved precision and accuracy, resulting in an AUC of 96.92%. The results revealed that the model has a 96.92% AUC in predicting accident severity. The work can be extended to investigate the complex correlations between a few key parameters and accident severity.

Landslide Susceptibility Mapping Using Machine Learning: A Case Study of Oregon

Landslide susceptibility assessment, a crucial component of disaster prevention and mitigation, has traditionally relied on geological datasets and commonly used evaluation metrics. However, these metrics, often applied to 2D susceptibility maps, may not capture the full complexity of the issue. In this study, we incorporated spatial distribution data, including a historical landslide inventory, and integrated morphological, geological, hydrological, and land-use features. This approach enabled the construction of predictive models using eight distinct algorithms. The evaluation of classifier performance scores unveiled the superior performance of gradient tree boosting. In contrast, logistic regression struggled to handle the nonlinear aspects of landslide susceptibility analysis. A finding in our research was the consistent disparity in predictive susceptibility maps, even when similar performance scores were achieved across different algorithms. This underscores the necessity of combining evaluation metrics with spatial mapping in landslide susceptibility model assessment. We also highlighted the critical role of digital elevation models in constructing effective models when feature data was limited. Conversely, when abundant information was available, the integration of multi-source data significantly enhanced the precision of landslide susceptibility mapping. Overall, this study provides valuable insights for spatial prioritization in landslide field investigations and enhances our understanding of landslide risk assessment.

Artificial Intelligence in Ship Trajectory Prediction

Maritime traffic is increasing more and more, creating more complex navigation environments for ships. Ship trajectory prediction based on historical AIS data is a vital method of reducing navigation risks and enhancing the efficiency of maritime traffic control. At present, employing machine learning or deep learning techniques to construct predictive models based on AIS data has become a focal point in ship trajectory prediction research. This paper systematically evaluates various trajectory prediction methods, spanning classical machine learning approaches and emerging deep learning techniques, to uncover their respective merits and drawbacks. In this work, a variety of studies were investigated that applied different algorithms in ship trajectory prediction, including regression models (RMs), artificial neural networks (ANNs), Kalman filtering (KF), and random forests (RFs) in machine learning, along with deep learning such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short-term memory (LSTM), gate recurrent unit (GRU) networks, and sequence-to-sequence (Seq2seq) networks. The performance of predictive models based on different algorithms in trajectory prediction tasks was graded and analyzed. Among the existing studies, deep learning methods exhibit significant performance and considerable potential application value for maritime traffic systems, which can be assessed by future work on ship trajectory prediction research.

Coverage-enhanced fault diagnosis for Deep Learning programs: A learning-based approach with hybrid metrics

Context:Given the data-driven paradigm inherent to Deep Learning (DL), it is inevitable that DL software will exhibit incorrect behavior in real-world applications. DL programs have been identified as a primary source of DL faults. To tackle this, researchers have devised a unique framework that approaches fault diagnosis as a learning task, which leverages runtime data as metrics to construct predictive models, enabling effective fault diagnosis. Object:In this paper, we aim to propose new metrics, especially from the coverage view, to enhance the performance of fault diagnosis models. Method:We combine coverage criteria and statistical operators to propose 80 coverage metrics, which summarize the trend of coverage values in the model training procedure. We construct hybrid prediction models by combining our new coverage metrics and existing runtime metrics under four widely used classifiers. Results:To examine whether adding our new coverage metrics performs well in DL program fault diagnosis, we conduct our experiments on six widely used datasets under four indicators (i.e., accuracy, F1 score, AUC, and MCC). Through the experiments, we observe that (a) coverage metrics are not redundant with respect to the original runtime metrics, and (b) adding extra coverage metrics can significantly enhance the performance of fault diagnosis models. Conclusions:Our study shows that our proposed coverage metrics are helpful in constructing effective fault diagnosis models for DL programs.

Identification of Potential Injury Risk Factors and Prediction Model Construction of Athletes using Data Mining Algorithm

Identification of potential injury risk factors and construction of prediction models for athletes using data mining algorithms involve analyzing various factors such as biomechanical, physiological, and environmental variables to determine their correlation with injury occurrences. Data mining techniques, such as decision trees, logistic regression, or neural networks, are then applied to identify patterns and relationships within the data. By integrating this information, predictive models can be developed to forecast the likelihood of athletes sustaining injuries based on their individual characteristics and training conditions. This paper introduces a novel approach for athlete injury risk prediction using the Noninvasive Data Mining Model with Multi-relational and Multi-dimensional Clustering (Ni-DMMMC) algorithm. By leveraging advanced data mining techniques, Ni-DMMMC aims to identify hidden relationships between various athlete characteristics, including biomechanical risk, training load, physiological markers, and environmental factors, to predict injury susceptibility accurately. Through multi-relational and multi-dimensional clustering, the algorithm effectively categorizes athletes into distinct clusters based on their unique risk profiles. These clusters provide valuable insights into the diverse injury risk profiles present within athlete populations, enabling targeted intervention strategies and personalized athlete management approaches. The proposed approach holds significant promise for enhancing injury prevention efforts, optimizing athlete performance, and improving overall well-being in sports medicine practice. athletes in Cluster 1 exhibit high biomechanical risk (0.85), moderate training load (0.60), low physiological markers (0.25), and moderate environmental risk (0.45), while athletes in Cluster 2 display moderate biomechanical risk (0.70), high training load (0.90), high physiological markers (0.80), and low environmental risk (0.30). These numerical values serve as indicators for assessing an athlete's injury risk profile comprehensively.

Research on the Driving Factors and Prediction Model of Urban Underground Space Demand in China

The development and utilization of urban underground space (UUS) have emerged as critical strategies to address the challenges posed by urban population growth and land resource depletion. Accurate prediction of UUS demand serves as the cornerstone for scientifically planning underground space and promoting sustainable urban development. In this study, statistical analysis methods were used to investigate the relationship between potential driving factors and UUS demand based on collected data from 16 cities in China. The identification of primary driving factors involves correlation, path, and determination coefficient analyses. Subsequently, univariate regression, multiple linear regression, and LASSO regression methods are employed to construct prediction models for UUS demand. Additionally, the link between historical data and UUS demand in each city was studied separately. The findings reveal that GDP per km2 and GDP per capita comprehensively capture the influence of urban population, economy, and transportation on UUS demand. Notably, GDP per km2 makes the most significant contribution to the proposed regression models, followed by GDP per capita. The application of LASSO regression proves effective in selecting potential factors while maximizing data utilization, presenting itself as a valuable auxiliary tool for UUS planning.