Search

Software engineering workflows use version control systems to track changes and handle merge cases from multiple contributors. This has introduced challenges to testing because it is impractical to test whole codebases to ensure each change is defect-free, and it is not enough to test changed files alone. Just-in-time software defect prediction (JIT-SDP) systems have been proposed to solve this by predicting the likelihood that a code change is defective. Numerous techniques have been studied to build such JIT software defect prediction models, but the power of pre-trained code transformer language models in this task has been underexplored. These models have achieved human-level performance in code understanding and software engineering tasks. Inspired by that, we modeled the problem of change defect prediction as a text classification task utilizing these pre-trained models. We have investigated this idea on a recently published dataset, ApacheJIT, consisting of 44k commits. We concatenated the changed lines in each commit as one string and augmented it with the commit message and static code metrics. Parameter-efficient fine-tuning was performed for 4 chosen pre-trained models, JavaBERT, CodeBERT, CodeT5, and CodeReviewer, with either partially frozen layers or low-rank adaptation (LoRA). Additionally, experiments with the Local, Sparse, and Global (LSG) attention variants were conducted to handle long commits efficiently, which reduces memory consumption. As far as the authors are aware, this is the first investigation into the abilities of pre-trained code models to detect defective changes in the ApacheJIT dataset. Our results show that proper fine-tuning improves the defect prediction performance of the chosen models in the F1 scores. CodeBERT and CodeReviewer achieved a 10% and 12% increase in the F1 score over the best baseline models, JITGNN and JITLine, when commit messages and code metrics are included. Our approach sheds more light on the abilities of language models in software engineering tasks, promoting their use in production environments and ensuring that deployed software is defect-free efficiently. [ABSTRACT FROM AUTHOR]

In recent years, the vigorous development of e-commerce has also greatly promoted the development of the fashion multimedia field. Fashion compatibility modeling plays a very important role in a series of applications, such as fashion retrieval and personalized recommendation. Because fashion compatibility prediction usually contains multiple modal information, in this paper, we present a type-aware fashion compatibility prediction model based on a hybrid attention mechanism that is centered on using a priori category information for the fusion of multimodal information. Specifically, the model first designs a hybrid attention mechanism to fully explore the inner dependency of the visual modality while enriching with textual modalities to obtain a joint feature representation of multimodal information. Furthermore, the model matches fashion items as a distance measurement problem, and the joint feature representation of multimodal information realizes type-aware characteristics by the design of a distance measurement function with category-aware embedding. The experimental results obtained on the publicly available Polyvore and Polyvore-D datasets demonstrate the effectiveness of the model. [ABSTRACT FROM AUTHOR]

Continuously reinforced concrete pavement (CRCP), crucial for the resilience of transportation infrastructure owing to its continuous steel reinforcement, confronts a critical challenge in the form of spalling—a distress phenomenon posing a threat to pavement durability and overall structural integrity. The detachment or breakage of concrete from the surface compromises CRCP's functionality and raises safety concerns and escalating maintenance costs. To address this pressing issue, our study investigates the multifaceted factors influencing spalling, employing a comprehensive approach that integrates statistical and machine learning techniques for predictive modeling. Descriptive statistics meticulously profile the dataset, emphasizing age, thickness, precipitation, temperature, and traffic parameters. Regression analysis unveils key relationships, emphasizing the significance of age, annual temperature, annual precipitation, maximum humidity, and the initial International Roughness Index (IRI) as influential factors. The correlation matrix heatmap guides feature selection, elucidating intricate interdependencies. Simultaneously, feature importance analysis identifies age, Average Annual Daily Traffic (AADT), and total pavement thickness as crucial contributors to spalling. In machine learning, adopting models, including Gaussian Process Regression and ensemble tree models, is grounded in their diverse capabilities and suitability for the complex task at hand. Their varying predictive accuracies underscore the importance of judicious model selection. This research advances pavement engineering practices by offering nuanced insights into factors influencing spalling in CRCP, refining our understanding of spalling influences. Consequently, the study not only opens avenues for developing improved predictive methodologies but also enhances the durability of CRCP infrastructure, addressing broader implications for informed decision-making in transportation infrastructure management. The selection of Gaussian Process Regression and ensemble tree models stems from their adaptability to capture intricate relationships within the dataset, and their comparative performance provides valuable insights into the diverse predictive capabilities of these models in the context of CRCP spalling. [ABSTRACT FROM AUTHOR]

Box office prediction is of great significance for understanding investment risks, class construction, promotion and distribution, and theater scheduling. However, due to the insufficient selection of influencing factors of movie box office, the currently existing prediction model restricts the prediction accuracy. A total of 34 influencing factors in 11 categories, such as heat index, movie types, release date, creators, first-day box office, were selected to study the prediction technology of movie box office. The Word2vec algorithm is used to construct a feature thesaurus for nouns in movie domain; adjectives and verbs with emotional coloring are used to construct an emotional dictionary based on the movie domain; and the TF-IDF algorithm is integrated to calculate the emotional scores of movie comments. A prediction method based on comments and Multivariate Linear Regression (MLR) is designed to analyze the relationship between the influencing factors and the movie box office, which provides an important basis for the prediction of the total box office, and also provides a decision-making reference for the movie industry and the related management departments. Incorporating comments as feature values to improve the accuracy, a prediction model based on comments and Convolutional Neural Network (CNN) is constructed. The results show that the average prediction accuracy of the MLR without comments, Back-Propagation Neural Network (BPNN), and CNN is 63.4%, 68.3%, and 71.9%, respectively, and after integrating the comments, the average prediction accuracy of the MLR and CNN is improved by 16.1% and 11.8%, respectively, and the prediction accuracy is significantly improved. [ABSTRACT FROM AUTHOR]

This study investigated whether machine learning (ML) has better predictive accuracy than logistic regression analysis (LR) for gait independence at discharge in subacute stroke patients (n = 843) who could not walk independently at admission. We developed prediction models using LR and five ML algorithms—specifically, the decision tree (DT), support vector machine, artificial neural network, ensemble learning, and k-nearest neighbor methods. Functional Independence Measure sub-items were used to evaluate the ability to walk independently. Model predictive accuracies were evaluated using areas under receiver operating characteristic curves (AUCs) as well as accuracy, precision, recall, F1 score, and specificity. The AUC for DT (0.812) was significantly lower than those for the other algorithms (p < 0.01); however, the AUC for LR (0.895) did not differ significantly from those for the other models (0.893–0.903). Other performance metrics showed no substantial differences between LR and ML algorithms. In conclusion, the DT algorithm had significantly low predictive accuracy, and LR showed no significant difference in predictive accuracy compared with the other ML algorithms. As its predictive accuracy is similar to that of ML, LR can continue to be used for predicting the prognosis of gait independence, with additional advantages of being easily understandable and manually computable. [ABSTRACT FROM AUTHOR]

Due to the uncertainty of geological conditions during the tunneling process, advanced prediction of TBM tunneling parameters is significant for evaluating operational safety and efficiency, especially for real-time prediction of key tunneling parameters during the steady phase of TBM operation. At present, although there are studies on constructing predictive models based on machine learning algorithms, multiparameter prediction consistent with the actual tunneling process remains challenging due to the complexity of the TBM tunneling process and the numerous tunneling parameters. Therefore, this paper proposes a real-time multiple tunneling parameters prediction method of TBM steady phase based on dual recurrent neural networks. Firstly, the irregular multidimensional time series of tunneling parameters are analyzed and processed, which are divided into an idle-push phase, a rising phase, and a steady phase; secondly, the parameters of rising phase are analyzed using a recurrent neural network, and the parameters relevant for constructing a real-time prediction model are screened; then, based on the screened parameters, the Bayesian-optimized gated recurrent unit (GRU, a kind of recursive neural network) is proposed to construct a real-time prediction model for the four key tunneling parameters during the steady phase. Finally, the effectiveness and practicality of the proposed method are demonstrated by verification on real TBM tunnel datasets and comparing it with the models constructed by six commonly used machine learning algorithms. The results of this paper show that the designed prediction method is able to achieve a good combination of performance in terms of accuracy and computational time-consumption, with an average prediction accuracy of 91.1% for the four parameters for different rock grades of geology, the multiparameter prediction time for 100 samples is only 11 ms. In addition, three current similar studies using deep learning methods were compared to demonstrate the superiority of this proposal. As a method more closer to practical application, this work provides guidance for the forward-looking prediction of TBM tunneling parameters. [ABSTRACT FROM AUTHOR]

An unsupervised change point detection (CPD) framework assisted by a predictive machine learning model called "Predict and Compare" is introduced which is able to detect change points online under the presence of non-trivial trend patterns which must be prevented from triggering false positives. Different predictive models for the required time series forecasting (Predict) step together with different statistical tests for deciding about the proximity of predicted and actual data (Compare step) are allowed. Its performance is shown for the Predict step being carried out by either an LSTM recursive neural network or an ARIMA linear time series model together with the CUSUM rule as Compare step method. It shows to perform best in comparison to several other online CPD methods for detect times in the regime of low numbers of false positive detections. The method's good performance is based on its ability to detect structural changes in the presence complex underlying trend patterns. The use case concerns tribological wear for which change points separating the run-in, steady-state, and divergent wear phases are detected. [ABSTRACT FROM AUTHOR]

Existing concrete creep coefficient prediction models have the limitation of not considering the structural characteristics of CFT. For this reason, these models tend to overestimate the creep deformation of CFT. Therefore, in order to overcome the limitations of existing CFT creep experiments, this study proposes a creep-experiment method involving the use of CFT that passively changes the load applied to a single concrete specimen by calculating the stress redistribution between the concrete and a steel tube in CFT based on a step-by-step method. Furthermore, by actually applying the proposed experimental method, a creep experiment of CFT lasting for approximately 163 days was performed and a superficial creep coefficient model of CFT was proposed based on long-term strain data from the experiment. In order to verify the proposed superficial creep coefficient model, it was compared with two design criteria (CEB-FIP and ACI) based on the experimental results of this study and references. As a result, compared to the existing design criteria, the value predicted by the proposed superficial creep coefficient model showed good agreement with the experimental results of this study and the references, proving that the proposed creep-experiment method of CFT and superficial creep coefficient model are reasonable. [ABSTRACT FROM AUTHOR]

Prediction of water-conducting fractured zone (WCFZ) of mine overburden is the premise for reducing or eliminating water inrush hazards in undersea mining. To obtain a more robust and precise prediction of WCFZ in undersea mining, a WCFZ prediction dataset with 122 cases of fractured zones was constructed. Five machine learning algorithms (linear regression, XGBRegressor, RandomForestRegressor, LineareSVR, and KNeighborsRegressor) were employed to develop five corresponding predictive models, taking multiple factors into account.The optimal parameters for each model are obtained through ten-fold cross-validation (10CV). The model's predictive performance was validated and assessed using two metrics, namely the coefficient of determination (R2) and mean squared error (MSE). A comparison was made with the regression performance of commonly used empirical formulas. The results indicate that the constructed model outperforms reliance solely on theoretical criteria, showing a high R2 value of up to 0.925 and a low MSE value of 3.61. The proposed model was validated in a recently established mining area on Sanshan Island, China. It shows low absolute and relative errors of 0.71 m and 2.01%, respectively, between the predicted value from the model and observation result from the field, demonstrating a high level of consistency with on-site conditions. This paves a path to leveraging machine learning algorithms for predicting the height of WCFZ. [ABSTRACT FROM AUTHOR]

A dislocation-density based crystalline plasticity (DCP) and nonlinear finite element (FE) analysis were used to predict, and fundamentally understand how and why fracture nucleation and propagation are related to the interrelated microstructural mechanisms of dislocation-density pileups, GB structure, orientation, and total and partial dislocation density interactions within and adjacent for a random low angle grain boundary (LAGB) and a random high angle GB (HAGB). The GB orientations and structures were obtained from micropillar experiments, such that LAGBs and the HAGBs can be accurately represented and used for the modeling predictions. The normal stress, density of pileups, and dislocation-density accumulation along and within the GB were higher for the low angle GB bicrystal. These interrelated phenomena delineate how fracture for high angle GBs nucleate and propagate at lower nominal strains than the lower angle GB bicrystal case. These predictions underscore how fundamental mechanisms can be identified and used to understand how failure nucleates and propagates for different GB structures and orientations. [ABSTRACT FROM AUTHOR]

Microbes have been demonstrated to be closely linked to diseases that pose a major threat to human health. Computing technologies can help researchers find potential microbe-drug associations more quickly and precisely. In this study, we introduced a novel computational prediction model called GLNNMDA based on global and local features of microbes and drugs to infer possible microbe-drug correlations. In GLNNMDA, we first constructed a heterogeneous network based on known microbe-drug relationships by integrating multiple similarity metrics of drugs and microbes. Subsequently, low-dimensional features will be extracted for nodes in the heterogeneous network by adopting the graph attention encoder. Next, based on combining these low-dimensional features with multiple properties of microbes and drugs to form a new comprehensive feature matrix, we would utilize the GLF module to extract the global and local features for microbes and drugs respectively, and then, we would further fuse these global and local features to come up with predictions of possible microbe-drug associations. Moreover, in order to evaluate the prediction performance of GLNNMDA, under the framework of fivefold cross-validation, intensive comparative experiments and case studies were done on different well-known public databases. The results showed that GLNNMDA obtained the highest AUC values as well as AUPR values of 0.9802 ± 0.0011, 0.9773 ± 0.0021 and 0.8586 ± 0.0004, 0.8008 ± 0.0031 in the two databases, MDAD and aBiofilm, respectively, compared to the state-of-the-art competing prediction methods. In addition, case studies of well-known microorganisms and drugs have demonstrated the effectiveness of GLNNMDA in inferring potential microbial drug associations, which implies that GLNNMDA may be a useful tool for microbe-drug association prediction in the future. The source code is available at: "https://github.com/KuangHaiYue/GLNNMDA.git". [ABSTRACT FROM AUTHOR]

In intensive care unit (ICU) patients undergoing mechanical ventilation (MV), the occurrence of difficult weaning contributes to increased ventilator-related complications, prolonged hospitalization duration, and a significant rise in healthcare costs. Therefore, early identification of influencing factors and prediction of patients at risk of difficult weaning can facilitate early intervention and preventive measures. This study aimed to strengthen airway management for ICU patients by constructing a risk prediction model with comprehensive and individualized offline programs based on machine learning techniques. This study involved the collection of data from 487 patients undergoing MV in the ICU, with a total of 36 variables recorded. The dataset was divided into a training set (70% of the data) and a test set (30% of the data). Five machine learning models, namely logistic regression, random forest, support vector machine, light gradient boosting machine, and extreme gradient boosting, were compared to predict the risk of difficult weaning in ICU patients with MV. Significant influencing factors were identified based on the results of these models, and a risk prediction model for ICU patients with MV was established. When evaluating the models using AUC (Area under the Curve of ROC) and Accuracy as performance metrics, the Random Forest algorithm exhibited the best performance among the five machine learning algorithms. The area under the operating characteristic curve for the subjects was 0.805, with an accuracy of 0.748, recall (0.888), specificity (0.767) and F1 score (0.825). This study successfully developed a risk prediction model for ICU patients with MV using a machine learning algorithm. The Random Forest algorithm demonstrated the highest prediction performance. These findings can assist clinicians in accurately assessing the risk of difficult weaning in patients and formulating effective individualized treatment plans. Ultimately, this can help reduce the risk of difficult weaning and improve the quality of life for patients. [ABSTRACT FROM AUTHOR]

Background: Haemoglobin variation (ΔHb) induced by fluid transfer through the intestitium has been proposed as a useful tool for detecting hydrostatic pulmonary oedema (HPO). However, its use in the emergency department (ED) setting still needs to be determined. Methods: In this observational retrospective monocentric study, ED patients admitted for acute dyspnoea were enrolled. Hb values were recorded both at ED presentation (T0) and after 4 to 8 h (T1). ΔHb between T1 and T0 (ΔHbT1-T0) was calculated as absolute and relative value. Two investigators, unaware of Hb values, defined the cause of dyspnoea as HPO and non-HPO. ΔHbT1-T0 ability to detect HPO was evaluated. A machine learning approach was used to develop a predictive tool for HPO, by considering the ability of ΔHb as covariate, together with baseline patient characteristics. Results: Seven-hundred-and-six dyspnoeic patients (203 HPO and 503 non-HPO) were enrolled over 19 months. Hb levels were significantly different between HPO and non-HPO patients both at T0 and T1 (p < 0.001). ΔHbT1-T0 were more pronounced in HPO than non-HPO patients, both as relative (-8.2 [-11.2 to -5.6] vs. 0.6 [-2.1 to 3.3] %) and absolute (-1.0 [-1.4 to -0.8] vs. 0.1 [-0.3 to 0.4] g/dL) values (p < 0.001). A relative ΔHbT1-T0 of -5% detected HPO with an area under the receiver operating characteristic curve (AUROC) of 0.901 [0.896–0.906]. Among the considered models, Gradient Boosting Machine showed excellent predictive ability in identifying HPO patients and was used to create a web-based application. ΔHbT1-T0 was confirmed as the most important covariate for HPO prediction. Conclusions: ΔHbT1-T0 in patients admitted for acute dyspnoea reliably identifies HPO in the ED setting. The machine learning predictive tool may represent a performing and clinically handy tool for confirming HPO. [ABSTRACT FROM AUTHOR]

Background: Prostate cancer is well known as the commonest cancer in men and the second leading cause of cancer-related death. CT, MRI and bone scintigraphy are considered the commonly widely used imaging diagnostic tools for detection, staging and follow-up of prostate cancer. Prostate-specific membrane antigen (PSMA) is a membrane glycoprotein, that can be concentrated in prostate cancer cells up to 100 times higher than in normal cells. PSMA-targeted imaging modalities have now proven their efficacy in diagnosis, staging and follow-up of prostate cancer. The use of 68Ga PSMA PET-CT has efficiently improved the detection of loco-regional and metastatic disease. 68Ga PSMA PET-CT also has an effective role in the primary diagnosis, staging, and detecting biochemical recurrence after curative treatment and in metastasis-targeted therapy. This work aims to review the role of 68Ga PSMA PET-CT in anatomical staging of prostate cancer in correlation with histopathological staging. Results: Zonal correlation between 68Ga PSMA findings and biopsy results showed sensitivity ranging between 76.9 and 90.6% and specificity ranging from 85.7 to 100%. There was high significant correlation between the SUVmax uptake and the biopsy results, between the SUVmax uptake and the local staging as well as between the Gleason score and 68Ga PSMA PET/CT findings. Conclusions: 68Ga PSMA PET/CT is a highly promising imaging modality with an effective role in detection of prostate cancer showing high sensitivity and specificity in prediction of zonal histopathological results and loco-regional Gleason score staging with significant positive correlation between the SUV uptake results, Gleason score and the PSA levels. [ABSTRACT FROM AUTHOR]

Transferring and replicating predictive algorithms across healthcare systems constitutes a unique yet crucial challenge that needs to be addressed to enable the widespread adoption of machine learning in healthcare. In this study, we explored the impact of important differences across healthcare systems and the associated Electronic Health Records (EHRs) on machine-learning algorithms to predict mental health crises, up to 28 days in advance. We evaluated both the transferability and replicability of such machine learning models, and for this purpose, we trained six models using features and methods developed on EHR data from the Birmingham and Solihull Mental Health NHS Foundation Trust in the UK. These machine learning models were then used to predict the mental health crises of 2907 patients seen at the Rush University System for Health in the US between 2018 and 2020. The best one was trained on a combination of US-specific structured features and frequency features from anonymized patient notes and achieved an AUROC of 0.837. A model with comparable performance, originally trained using UK structured data, was transferred and then tuned using US data, achieving an AUROC of 0.826. Our findings establish the feasibility of transferring and replicating machine learning models to predict mental health crises across diverse hospital systems. [ABSTRACT FROM AUTHOR]

While genome-wide association studies are valuable in identifying CRC survival predictors, the benefit of adding blood DNA methylation (blood-DNAm) to clinical features, including the TNM system, remains unclear. In a multi-site population-based patient cohort study of 2116 CRC patients with baseline blood-DNAm, we analyzed survival predictions using eXtreme Gradient Boosting with a 5-fold nested leave-sites-out cross-validation across four groups: traditional and comprehensive clinical features, blood-DNAm, and their combination. Model performance was assessed using time-dependent ROC curves and calibrations. During a median follow-up of 10.3 years, 1166 patients died. Although blood-DNAm-based predictive signatures achieved moderate performances, predictive signatures based on clinical features outperformed blood-DNAm signatures. The inclusion of blood-DNAm did not improve survival prediction over clinical features. M1 stage, age at blood collection, and N2 stage were the top contributors. Despite some prognostic value, incorporating blood DNA methylation did not enhance survival prediction of CRC patients beyond clinical features. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) presents diverse symptoms and comorbidities, complicating its diagnosis and management. The primary objective of this cross-sectional, monocentric study was to assess digital gait sensor data's utility for monitoring and diagnosis of motor and gait impairment in PD. As a secondary objective, for the more challenging tasks of detecting comorbidities, non-motor outcomes, and disease progression subgroups, we evaluated for the first time the integration of digital markers with metabolomics and clinical data. Using shoe-attached digital sensors, we collected gait measurements from 162 patients and 129 controls in a single visit. Machine learning models showed significant diagnostic power, with AUC scores of 83–92% for PD vs. control and up to 75% for motor severity classification. Integrating gait data with metabolomics and clinical data improved predictions for challenging-to-detect comorbidities such as hallucinations. Overall, this approach using digital biomarkers and multimodal data integration can assist in objective disease monitoring, diagnosis, and comorbidity detection. [ABSTRACT FROM AUTHOR]

CRISPR is a precise and effective genome editing technology; but despite several advancements during the last decade, our ability to computationally design gRNAs remains limited. Most predictive models have relatively low predictive power and utilize only the sequence of the target site as input. Here we suggest a new category of features, which incorporate the target site genomic position and the presence of genes close to it. We calculate four features based on gene expression and codon usage bias indices. We show, on CRISPR datasets taken from 3 different cell types, that such features perform comparably with 425 state-of-the-art predictive features, ranking in the top 2–12% of features. We trained new predictive models, showing that adding expression features to them significantly improves their r2 by up to 0.04 (relative increase of 39%), achieving average correlations of up to 0.38 on their validation sets; and that these features are deemed important by different feature importance metrics. We believe that incorporating the target site's position, in addition to its sequence, in features such as we have generated here will improve our ability to predict, design and understand CRISPR experiments going forward. [ABSTRACT FROM AUTHOR]

Background: Severe trauma is the leading cause of disability and mortality in the patients under 35 years of age. Surgical site infections (SSI) represent a significant complication in this patient population. However, they are often inadequately investigated, potentially impacting the quality of patient outcomes. The aim of this study was to investigate the epidemiology of SSI and risk factors in severe trauma patients. Methods: We conducted a multicenter retrospective cohort study screening the severe trauma patients (STP) admitted to two intensive care units of an academic institution in Marseille between years2018 and 2019. Those who underwent orthopedic or spinal surgery within 5 days after admission were included and classified into two groups according to the occurrence of SSI (defined by the Centers for Disease Control (CDC) international diagnostic criteria) or not. Our secondary goal was to evaluate STP survival at 48 months, risk factors for SSI and microbiological features of SSI. Results: Forty-seven (23%) out of 207 STP developed an SSI. Mortality at 48-months did not differ between SSI and non-SSI patients (12.7% vs. 10.0%; p = 0.59). The fractures of 22 (47%) severe trauma patients with SSI were classified as Cauchoix 3 grade and 18 (38%) SSI were associated with the need for external fixators. Thirty (64%) severe trauma patients with SSI had polymicrobial infection, including 34 (72%) due to Gram-positive cocci. Empirical antibiotic therapy was effective in 31 (66%) cases. Multivariate analysis revealed that risk factors such as low hemoglobin, arterial oxygenation levels, hyperlactatemia, high serum creatinine and glycemia, and Cauchoix 3 grade on the day of surgery were associated with SSI in severe trauma patients. The generated predictive model showed a good prognosis performance with an AUC of 0.80 [0.73–0.88] and a high NPV of 95.9 [88.6–98.5] %. Conclusions: Our study found a high rate of SSI in severe trauma patients, although SSI was not associated with 48-month mortality. Several modifiable risk factors for SSI may be effectively managed through enhanced perioperative monitoring and the implementation of a patient blood management strategy. [ABSTRACT FROM AUTHOR]

This study focuses on predicting the prognosis of acute ischemic stroke patients with focal neurologic symptoms using a combination of diffusion-weighted magnetic resonance imaging (DWI) and clinical information. The primary outcome is a poor functional outcome defined by a modified Rankin Scale (mRS) score of 3–6 after 3 months of stroke. Employing nnUnet for DWI lesion segmentation, the study utilizes both multi-task and multi-modality methodologies, integrating DWI and clinical data for prognosis prediction. Integrating the two modalities was shown to improve performance by 0.04 compared to using DWI only. The model achieves notable performance metrics, with a dice score of 0.7375 for lesion segmentation and an area under the curve of 0.8080 for mRS prediction. These results surpass existing scoring systems, showing a 0.16 improvement over the Totaled Health Risks in Vascular Events score. The study further employs grad-class activation maps to identify critical brain regions influencing mRS scores. Analysis of the feature map reveals the efficacy of the multi-tasking nnUnet in predicting poor outcomes, providing insights into the interplay between DWI and clinical data. In conclusion, the integrated approach demonstrates significant advancements in prognosis prediction for cerebral infarction patients, offering a superior alternative to current scoring systems. [ABSTRACT FROM AUTHOR]

Shear strength (SS) parameters are essential for understanding the mechanical behavior of materials, particularly in geotechnical engineering and rock mechanics. This study proposes a novel hierarchical ensemble model (HEM) to predict SS parameters: cohesion (C ) and angle of internal friction (φ ). The HEM addresses the limitations of traditional machine learning models. Its performance was validated using leave-one-out cross-validation (LOOCV) and out-of-bag (OOB) evaluation methods. The model's accuracy was assessed with R-squared correlation (R2), absolute average relative error percentage (AAREP), Taylor diagrams, and quantile–quantile plots. The computational results demonstrated that the proposed HEM outperforms previous studies using the same database. The model predicted φ and C with R2 values of 0.93 and 0.979, respectively. The AAREP values were 1.96% for φ and 4.7% for C . These results indicate that the HEM significantly improves the prediction quality of φ and C , and exhibits strong generalization capability. Sensitivity analysis revealed that σ_3maxσ3max (maximum principal stress) had the greatest impact on modeling both φ and C . According to uncertainty analysis, the LOOCV and OOB had the widest uncertainty bands for the φ and C parameters, respectively. [ABSTRACT FROM AUTHOR]

The use of machine learning techniques to identify problem gamblers has been widely established. However, existing methods often rely on self-reported labeling, such as temporary self-exclusion or account closure. In this study, we propose a novel approach that combines two documented methods. First we create labels for problem gamblers in an unsupervised manner. Subsequently, we develop prediction models to identify these users in real-time. The methods presented in this study offer useful insights that can be leveraged to implement interventions aimed at guiding or discouraging players from engaging in disordered gambling behaviors. This has potential implications for promoting responsible gambling and fostering healthier player habits. [ABSTRACT FROM AUTHOR]

To enhance the accuracy of hydrodynamic forces predictions for underwater vehicle within certain resource constraints, this study integrates high and low-fidelity samples using the Co-Kriging method, combined with an expected improvement (EI) sequential infill criterion to construct a hydrodynamic forces prediction model. Different grid densities of computational fluid dynamics (CFD) calculations are used to distinguish high and low-fidelity samples. Taking the Joubert BB2 underwater vehicle as the research object, hydrodynamic forces predictions are conducted for various angles of attack and speeds. The effectiveness of the EI infill criterion in improving model prediction accuracy is validated. Furthermore, compared to the traditional Kriging model under the same computational resources, the Co-Kriging method, which integrates high and low-fidelity samples, significantly outperforms the Kriging model constructed solely from high or low-fidelity samples in overall prediction accuracy for underwater vehicle hydrodynamic forces. [ABSTRACT FROM AUTHOR]

Louisiana Department of Transportation and Development (DOTD) pavement preservation program consists of various pavement preservation treatments, including single, double, and triple chip seals. Such treatments are applied mainly to collectors and local roads. Louisiana DOTD has spent substantial financial resources on various rehabilitation and maintenance treatments to minimize the pavement distresses and improve the pavement life. However, the effectiveness of any treatment largely depends on the time of treatment and trigger governed by treatment performance models. This study focuses on the performance evaluation of chip seal treatment on flexible pavements using the before and after treatment performance data. The treatment benefits in terms of remaining service life, service life extension, and treatment life were evaluated using the treatment transition matrix. Such analysis yielded effective treatment trigger values for each distress type. In addition, the before and after treatment data were utilized to develop IRI and transverse cracking prediction models for chip seal treatment on flexible pavements. [ABSTRACT FROM AUTHOR]

Purpose: This study aimed to calculate region and diagnosis‐specific minimal important changes (MICs) of the Foot and Ankle Outcome Score (FAOS) and the Foot and Ankle Ability Measure (FAAM) in patients requiring foot and ankle surgery and to assess their variability across different foot and ankle diagnoses. Methods: The study used routinely collected data from patients undergoing elective foot and ankle surgery. Patients had been invited to complete the FAOS and FAAM preoperatively and at 3–6 months after surgery, along with two anchor questions encompassing change in pain and daily function. Patients were categorised according to region of pathology and subsequent diagnoses. MICs were calculated using predictive modelling (MICPRED) and receiver operating characteristic curve (MICROC) method and evaluated according to strict credibility criteria. Results: Substantial variability of the MICs between forefoot and ankle/hindfoot region was observed, as well as among specific foot and ankle diagnoses, with MICPRED and MICROC values ranging from 7.8 to 25.5 points and 9.4 to 27.8, respectively. Despite differences between MICROC and MICPRED estimates, both calculation methods exhibited largely consistent patterns of variation across subgroups, with forefoot conditions systematically showing smaller MICs than ankle/hindfoot conditions. Most MICs demonstrated high credibility; however, the majority of the MICs for the FAOS symptoms subscale and forefoot conditions exhibited insufficient or low credibility. Conclusion: The MICs of the FAOS and FAAM vary across foot and ankle diagnoses in patients undergoing elective foot and ankle surgery and should not be used as a universal fixed value, but recognised as contextual parameters. This can help clinicians and researchers in more accurate interpretation of the FAOS and FAAM change scores. Level of Evidence: Level IV. [ABSTRACT FROM AUTHOR]

The existing machine learning-based energy efficiency and performance models for the servers have achieved high prediction accuracy with the support of abundant training data. However, the differences in data distribution among heterogeneous servers in cloud data centers make it impractical to apply a machine learning-based model trained on one server to another directly. Meanwhile, collecting sufficient data for new servers from scratch incurs expensive time costs. To address these challenges, a transfer regression-based method for cross-server energy efficiency and performance prediction, named FS-DBoost, is proposed to reduce the overhead of establishing the two prediction models by transferring feature importance and distribution knowledge from data of existing servers. Initially, to transfer feature importance information, a sparse regression model is introduced to learn a feature selection vector from the source domain. Then, we design a boosting-based transfer algorithm, DBoost, to train the models for the target server using data with selected features. DBoost adjusts the total weight of the target domain based on the relatedness between source and target domains. The experimental results demonstrate that FS-DBoost achieves an average performance improvement of over 10% on real-world datasets compared to six transfer regression methods. [ABSTRACT FROM AUTHOR]

Heart failure (HF) is a life-threatening disease affecting at least 64 million people worldwide. Hence, it places great stresses on patients and healthcare systems. Accordingly, providing a computerized model for HF prediction will help in enhancing diagnosis, treatment, and long-term management of HF. In this paper, we introduce a new guided attentive HF prediction approach. In this method, a sparse-guided feature ranking method is proposed. Firstly, a Gauss–Seidel strategy is applied to the preprocessed feature pool for low-rank approximation procedure with a trace-norm regularization. The resultant sparse attributes, after a Spearman ranking elimination, are employed to guide the original feature pool through linear translation-variant model. Then, a fast Newton-based method is employed for a non-negative matrix factorization for the guided feature pool. The resultant bases of the factorization process are finally utilized in the adopted deep attentive predictive model. For the final prediction stage, instead of the commonly used machine learning approaches, we introduce an attentive-based classifier. It employs sequential attention to choose the most proper salient features for efficient interpretability and learning process. For the evaluation of the proposed HF prediction model, three different datasets are employed, i.e., UCI, Faisalabad, and Framingham datasets. Compared to state-of-the-art techniques, the proposed approach outperforms their performance on all datasets with even small feature sizes. With only four feature bases, the proposed method achieves an average accuracy of 98%, while, with full feature bases, full accuracy is gained. [ABSTRACT FROM AUTHOR]

The objective of this research was to compare social, emotional, and cognitive determinants of depression and anxiety symptoms and mental wellbeing using the two-continua model of mental health and illness in two age groups. The two-continua model proposes that mental health and mental illness are not two ends of the same spectrum but are, in fact, two separate but related spectrums. This cross-sectional study used a multi-age group comparison approach to identify the relative predictive strengths of risk and protective factors for the two-continua model of mental health and mental illness. Participants (n = 458: 251 16–25 year olds, and 207 35–64 year olds) completed an online survey that measured the outcome variables of depression and anxiety symptoms and mental wellbeing. Independent variables from three conceptual areas in psychology—(1) positive psychology: optimism, pessimism, and accomplishment; (2) emotion regulation: cognitive reappraisal and expressive suppression; and (3) interpersonal theories: belonging and relationship with parent/child—were measured to ascertain the determinants of these outcome variables. The all-variables models explained 58–68% of the variance in depression symptoms, 77–80% in mental wellbeing, and 26–43% in anxiety symptoms. For both groups, the strongest predictor of mental wellbeing in these models was accomplishment. The strongest predictors in these models of mental illness symptoms differed between groups: belonging in the younger group and accomplishment in the older group. Programs targeting belonging and accomplishment could be highly effective in promoting mental wellbeing and reducing mental ill-health for these groups. Interventions require contextual investigation to locate drivers of mental wellbeing and illness for different age groups prior to implementation. [ABSTRACT FROM AUTHOR]

Objective: This study aims to develop a predictive model for estimating the likelihood of anemia of chronic disease (ACD) in patients with systemic lupus erythematosus (SLE) and to elucidate the relationship between various factors and ACD Methods: Individuals diagnosed with SLE for at least one year were enrolled and categorized into two groups: those with ACD and those without anemia symptoms. Patients were randomly assigned to training and test sets at an 8:2 ratio. The least absolute shrinkage and selection operator (LASSO) method was used to select predictors, followed by logistic regression for modeling. Model performance was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) for both training and test sets. Results: The study included a total of 216 patients, with 172 in the training set and 44 in the test set. LASSO identified 6 variables for constructing the predictive model, resulting in an area under the curve (AUC) of 0.833 (95% CI, 0.773-0.892) in the training set and 0.861 (95% CI, 0.750-0.972) in the test set. Calibration curves indicated consistency between expected and observed probabilities. DCA indicated that the model yielded a net benefit with threshold probabilities ranging from 20% to 90% in the training set and from 10% to 80% in the test set. Conclusion: This study presents a predictive model for assessing the risk of ACD in SLE patients. The model effectively captures the underlying mechanism of ACD in SLE and empowers clinicians to make well-informed treatment adjustments. Key Points • Development of a New Predictive Model: This study introduces a new predictive model to evaluate the likelihood of anemia of chronic disease (ACD) in patients with systemic lupus erythematosus (SLE). The model utilizes routine laboratory parameters to identify high-risk individuals, addressing a significant gap in current clinical practice. • Reflection of Potential Mechanisms for ACD Development: By incorporating the factors needed to construct the predictive model, this study also sheds light on the potential mechanisms of ACD development in SLE patients. [ABSTRACT FROM AUTHOR]

The parametrization of the oblique corrections through S, T, and U – later extended by V, W and X – is a convenient way of comparing the predictions for various electroweak observables at the one-loop level between the Standard Model and its extensions. That parametrization assumes that the extensions under consideration have S U (2) × U (1) gauge symmetry and the tree-level relation m W = m Z cos θ W between the Weinberg angle and the gauge-boson masses. In models where that relation does not hold at the Lagrangian level, the parameter T is not ultraviolet-finite, making the parametrization inadequate. We present expressions that parametrize the difference of the various predictions of two models with m W ≠ m Z cos θ W in terms of oblique parameters. The parameter T does not play a role in those expressions. Conveniently, they may be reached from the ones that were derived for models with tree-level m W = m Z cos θ W , by performing a simple substitution for T. We also discuss the difficulties in using oblique parameters when comparing a model with m W ≠ m Z cos θ W to the Standard Model. Finally, we compute the relevant five oblique parameters S, U, V, W and X in the SM extended by both, hypercharge Y = 0 and Y = 1 , triplet scalars. [ABSTRACT FROM AUTHOR]

Background: Artificial intelligence (AI) models have been applied in various medical imaging modalities and surgical disciplines, however the current status and progress of ultrasound-based AI models within hepatopancreatobiliary surgery have not been evaluated in literature. Therefore, this review aimed to provide an overview of ultrasound-based AI models used for hepatopancreatobiliary surgery, evaluating current advancements, validation, and predictive accuracies. Method: Databases PubMed, EMBASE, Cochrane, and Web of Science were searched for studies using AI models on ultrasound for patients undergoing hepatopancreatobiliary surgery. To be eligible for inclusion, studies needed to apply AI methods on ultrasound imaging for patients undergoing hepatopancreatobiliary surgery. The Probast risk of bias tool was used to evaluate the methodological quality of AI methods. Results: AI models have been primarily used within hepatopancreatobiliary surgery, to predict tumor recurrence, differentiate between tumoral tissues, and identify lesions during ultrasound imaging. Most studies have combined radiomics with convolutional neural networks, with AUCs up to 0.98. Conclusion: Ultrasound-based AI models have demonstrated promising accuracies in predicting early tumoral recurrence and even differentiating between tumoral tissue types during and after hepatopancreatobiliary surgery. However, prospective studies are required to evaluate if these results will remain consistent and externally valid. [ABSTRACT FROM AUTHOR]

Background: Laparoscopic pancreatoduodenectomy (LPD) is one of the most challenging operations and has a long learning curve. Artificial intelligence (AI) automated surgical phase recognition in intraoperative videos has many potential applications in surgical education, helping shorten the learning curve, but no study has made this breakthrough in LPD. Herein, we aimed to build AI models to recognize the surgical phase in LPD and explore the performance characteristics of AI models. Methods: Among 69 LPD videos from a single surgical team, we used 42 in the building group to establish the models and used the remaining 27 videos in the analysis group to assess the models' performance characteristics. We annotated 13 surgical phases of LPD, including 4 key phases and 9 necessary phases. Two minimal invasive pancreatic surgeons annotated all the videos. We built two AI models for the key phase and necessary phase recognition, based on convolutional neural networks. The overall performance of the AI models was determined mainly by mean average precision (mAP). Results: Overall mAPs of the AI models in the test set of the building group were 89.7% and 84.7% for key phases and necessary phases, respectively. In the 27-video analysis group, overall mAPs were 86.8% and 71.2%, with maximum mAPs of 98.1% and 93.9%. We found commonalities between the error of model recognition and the differences of surgeon annotation, and the AI model exhibited bad performance in cases with anatomic variation or lesion involvement with adjacent organs. Conclusions: AI automated surgical phase recognition can be achieved in LPD, with outstanding performance in selective cases. This breakthrough may be the first step toward AI- and video-based surgical education in more complex surgeries. [ABSTRACT FROM AUTHOR]

One of the preconditions for efficient cloud computing services is the continuous availability of services to clients. However, there are various reasons for temporary service unavailability due to routine maintenance, load balancing, cyber-attacks, power management, fault tolerance, emergency incident response, and resource usage. Live Virtual Machine Migration (LVM) is an option to address service unavailability by moving virtual machines between hosts without disrupting running services. Pre-copy memory migration is a common LVM approach used in cloud systems, but it faces challenges due to the high rate of frequently updated memory pages known as dirty pages. Transferring these dirty pages during pre-copy migration prolongs the overall migration time. If there are large numbers of remaining memory pages after a predefined iteration of page transfer, the stop-and-copy phase is initiated, which significantly increases downtime and negatively impacts service availability. To mitigate this issue, we introduce a prediction-based approach that optimizes the migration process by dynamically halting the iteration phase when the predicted downtime falls below a predefined threshold. Our proposed machine learning method was rigorously evaluated through experiments conducted on a dedicated testbed using KVM/QEMU technology, involving different VM sizes and memory-intensive workloads. A comparative analysis against proposed pre-copy methods and default migration approach reveals a remarkable improvement, with an average 64.91% reduction in downtime for different RAM configurations in high-write-intensive workloads, along with an average reduction in total migration time of approximately 85.81%. These findings underscore the practical advantages of our method in reducing service disruptions during live virtual machine migration in cloud systems. [ABSTRACT FROM AUTHOR]

This paper introduces and analyzes three innovative Linear Prediction (LP) models, consisting of two Fractional Order (FO) LP models and an integer LP model. The closed-form expressions for the proposed methods-namely, Two Parameter FO Linear Prediction (TP-FLP), FO Convex Linear Prediction (FCLP), and integer Convex Linear Prediction (CLP)-are derived for derivative order 0 ≤ α ≤ 2 . These derivations contribute to a more profound understanding of underlying mathematical principles of the proposed predictor. The foundation of our proposed methodologies is based on the presentation of the current signal sample as a linear combination of the FO derivative of two past samples, coupled with the utilization of the convex combination technique. An extensive set of experiments is conducted to compare the effectiveness of the proposed models with baseline methods involving two traditional LP models: First- and Second-order LP, along with the One Parameter FO Linear Prediction (OP-FLP) model. The performance evaluation encompasses a diverse range of signal types, including sinusoidal waves, damped sine waves, electroencephalogram (EEG), and speech signals. The simulation results demonstrate significant advancements achieved by the proposed models. Notably, the proposed FCLP exhibits a remarkable prediction gain of 24.74 dB, outperforming baseline methods such as OP-FLP, First- and Second-order LP models, that achieve prediction gains of 23.17, 23.15, and 10.14 dB, respectively. [ABSTRACT FROM AUTHOR]

Background: Diabetes mellitus (DM) increases the risk complications in addition to mortality. Quantifying the risk of complications using artificial intelligence could be a way to design comprehensive patient healthcare programs. Objective: Predicting the probability of macro and microvascular complications in patients with DM through Machine Learning. Methods: Retrospective cohort study. Based on an outpatient follow-up program for diabetic patients, 64,081 records and 287 variables were identified, with highly unbalanced data. Predictive models for chronic kidney disease (CKD), lower extremity amputation (LEA), coronary heart disease (CHD), and early mortality (MOR) were developed. An exhaustive computational method was conducted to find the best combination between machine learning (ML) algorithms and sampling method. Results: The best model was determined by assessing its performance through the heuristics obtained from a comprehensive analysis of the accuracy and F1 values for ML, sampling, and dataset. Regarding each complication, 99.9% accuracy was obtained for LEA, 94.3% for CHD, 97.4% for MOR, and 98.8% for CKD. F1 was assessed to identify false positives, with 84.5% for CKD, 63.6% for MOR, 46.2% for LEA, and 44.8% for CHD. Conclusions: This ML model can be applied to predict CHD, CKD, and MOR. The success of ML predictions lies in the clinical definition of initial variables and their simplification for obtaining variables based on which the algorithms can identify patients that are likely to develop a complication. For clinical application of this system, it is necessary to assess the cross performance of metrics, as found here (accuracy higher 95% and F1-Score higher than 80%). [ABSTRACT FROM AUTHOR]

Network reliability, named multistate stochastic cloud/edge-based network (MCEN) reliability afterwards, is defined as the probability that demands can be satisfied for an MCEN. It can be regarded as a performance indicator of the MCEN to measure the service capability. The concept of existing algorithms is to produce all of minimal system-state vectors for calculating MCEN reliability. However, such concept cannot response MCEN reliability in time when the MCEN scale becomes complicated in the Industry 4.0 environment. For providing MCEN reliability for decision making immediately, an architecture of a deep neural network (DNN) is developed to propose a prediction model for MCEN reliability such that MCEN capability with varied data can be learned promptly. To train the reliability prediction model, MCEN information is transformed to the suitable format, and the related information for DNN setting, including the determination of related functions, are defined with appropriate hyperparameters by using Bayesian Optimization. An illustrative case and a practical case of Amazon Web Service are provided to demonstrate the prediction model for MCEN reliability to show the availability and the efficiency. [ABSTRACT FROM AUTHOR]

Objective: The main aim of this study was to develop an equation for predicting performance in 42.2 km (MRT) using pacing and packing behavior, age group and previous 21.1 km time as possible explanatory variables. Methods: 1571 men and 251 female runners who took part in the Valencia Marathon and Half-Marathon were selected to display the regression models. Stepwise regression analysis showed as explanatory variables for MRT: pacing behavior, age group, and time in 21.1 km. Results: The analysis showed four regression models to estimate accurately MRT based principally on athletes previous performance in half-marathon and pacing behavior for men (R2= 0.72–0.88; RMSE= 4:03–8:31 [min:s]). For women, it was suggested a multiple linear regression for estimating MRT (R2 0.95; RSE= 8:06 [min:s]) based on previous performance in half-marathon and pacing behavior. The subsequent concordance analysis showed no significant differences between four of the total regressions with real time in the marathon (p>0.05). Conclusion: The present results suggest that even and negative pacing behavior and a better time in 21.1 km, in the previous weeks of the marathon, might accurately predict the MRT. At the same time, nomadic packing behavior was the one that reported the best performance. On the other hand, although the age group variable might partially explain the final performance, it should be included with caution in the final model because of differences in sample distribution, causing an overestimation or underestimation of the final time. [ABSTRACT FROM AUTHOR]

Panoramic video multimedia technology has made significant advancements in recent years, providing users with an immersive experience by displaying the entire 360° spherical scene centered around their virtual location. However, due to its larger data volume compared to traditional video formats, transmitting high-quality videos requires more bandwidth. It is important to note that users do not see the whole 360° content simultaneously, but only a portion that is within their viewport. To save bandwidth, viewport-based adaptive streaming has become a significant technology that transmits only the viewports of interest to the user in high quality. Therefore, the accuracy of viewport prediction plays a crucial role. However, the performance of viewport prediction is affected by the size of the prediction window, which decreases significantly as the window size increases. In order to address this issue, we propose an effective self-attention viewport prediction model based on distance constraint in this paper. Firstly, by analyzing the existing viewport trajectory dataset, we find the randomness and continuity of the viewport trajectory. Secondly, to solve the randomness problem, we design a viewport prediction model based on a self-attention mechanism to provide more trajectory information for long inputs. Thirdly, in order to ensure the continuity of the predicted viewport trajectory, the loss function is modified with the distance constraint to reduce the change in the continuity of prediction results. Finally, the experimental results based on the real viewport trajectory datasets show that the algorithm we propose has higher prediction accuracy and stability compared with the advanced models. [ABSTRACT FROM AUTHOR]

Purpose: Early identification of hematoma enlargement and persistent hematoma expansion (HE) in patients with cerebral hemorrhage is increasingly crucial for determining clinical treatments. However, due to the lack of clinically effective tools, radiomics has been gradually introduced into the early identification of hematoma enlargement. Though, radiomics has limited predictive accuracy due to variations in procedures. Therefore, we conducted a systematic review and meta-analysis to explore the value of radiomics in the early detection of HE in patients with cerebral hemorrhage. Methods: Eligible studies were systematically searched in PubMed, Embase, Cochrane and Web of Science from inception to April 8, 2024. English articles are considered eligible. The radiomics quality scoring (RQS) tool was used to evaluate included studies. Results: A total of 34 studies were identified with sample sizes ranging from 108 to 3016. Eleven types of models were involved, and the types of modeling contained mainly clinical, radiomic, and radiomic plus clinical features. The radiomics models seem to have better performance (0.77 and 0.73 C-index in the training cohort and validation cohort, respectively) than the clinical models (0.69 C-index in the training cohort and 0.70 C-index in the validation cohort) in discriminating HE. However, the C-index was the highest for the combined model in both the training (0.82) and validation (0.79) cohorts. Conclusions: Machine learning based on radiomic plus clinical features has the best predictive performance for HE, followed by machine learning based on radiomic features, and can be used as a potential tool to assist clinicians in early judgment. [ABSTRACT FROM AUTHOR]

We proposed here a non-destructive technology for pre-sorting eggs into subclasses characterized by a specifical acceptable shelf life and quality requirements. Egg characteristics were identified suiting a predictive model for controlling storage periods. Accordingly, the relationships of egg parameters were assessed, with weight loss (ΔW) during storage being the best indicator of changes in egg contents variables. Using changes in ΔW, we established three indicators with the maximum effect on fast egg drying and shrinkage. These included egg weight (W), egg volume-to-surface area ratio, and air cell diameter. The relationship formulae were derived to estimate the ΔW value accurately. This approach enables to judge regarding the potential of each particular egg subclass for its acceptable weight shrinkage and assign an optimal storage period for it. The proposed non-invasive analytical method can be implemented in industrial conditions for both table and hatching eggs with the available set of automated technological equipment. [ABSTRACT FROM AUTHOR]

Propensity score methods have been widely adopted in observational studies, however research on propensity score-based weighting (PSW) methods in complex survey data settings is lacking, particularly for binary outcomes. We conducted a simulation study to compare eight propensity score weighting approaches for estimating treatment effects using survey weighted data. Each of the eight methods is applied to estimation of two measures of the population-level treatment effect: the population average treatment effect (PATE), and the population average treatment effect on the treated (PATT). The methods are compared in terms of mean relative bias and coverage probability under different scenarios by varying the treatment effect, degrees of model misspecification, and levels of overlap in the propensity score. The results demonstrate that the two-stage methods with predicted outcomes weighted by survey weights consistently outperform the other methods for estimating the PATT; for estimating the PATE, the best performing PSW method depends on the degree of model misspecification and propensity score overlap. When the outcome model is correctly specified, four two-stage methods produce better estimates depending on the propensity score overlap. The methods are applied to the 2015 National Health Interview Survey data to estimate the effect of provider-patient discussion about smoking on smoking cessation. [ABSTRACT FROM AUTHOR]

Parkinson's disease is related to nervous system disorders in human beings. In this paper, the status of Parkinson's disease has been predicted based on the analysis of features of two Parkinson's disease symptoms: Dysphonia and Dysarthria. The Dysphonia symptom has been measured by analyzing the features extracted from the vocal sounds of a patient. The Dysarthria symptom of Parkinson's disease has been analyzed by the features extracted from the speech signals of a patient. Hence, two different prediction models have been built for deriving the status of Parkinson's disease. The derivation of these prediction systems is based on statistical and discriminant feature analysis. The statistical-based feature analysis is carried out using descriptive and inferential analysis. In contrast, the enteric, deviation, and correlation-based information between the features are utilized for descriptive analysis. The inferential analysis has been performed using hypothetical testing of the distribution of features. The descriptive and inferential feature analyses are used to derive effective features for the Parkinson's disease problem based on the Dysphonia and Dysarthria symptoms. In the discriminant feature analysis, the feature sets undergo deriving discriminant features. The best-selected features are used to build a prediction model for detecting Parkinson's disease problems in a patient. Extensive experimentation has been carried out using a Dysphonia dataset containing 195 samples. Each sample has 23 features. One dataset for Dysarthria symptoms contains 756 observations, with each observation having 754 features. The best prediction models that have been obtained correspond to these datasets, and 93.50% is obtained for Dysphonia and 87.63% for Dysarthria symptoms databases, respectively. The performance of the proposed system has been compared with some existing methods concerning each employed dataset, showing the superiority of the proposed approach. [ABSTRACT FROM AUTHOR]

The current extension limit prediction model for offshore extended-reach well (ERW) in mudstone does not consider the formation collapse, which poses a huge risk to offshore drilling construction. To address this problem, this paper presents new open-hole extension limit prediction model for ERW. By considering formation collapse, rate of penetration (ROP), and annular pressure loss, the extension limit models during normal drilling and tripping were derived. The sensitivity of geological and engineering factors was evaluated by analyzing limits for wells 1H and 2H. The research results showed that: (1) The extension limit increases with the ROP and formation collapse duration, but decreases with the increase in mud weight, plastic viscosity, and flow rate. (2) In ERWs, the mud flow rate has a significant impact on the extension limit than the plastic viscosity of mud fluid. However, mud weight has the least impact compared to the two. (3) Considering various parameters, the predicted extension limit of well 1H, when the mud weight is 1.16 g/cm3 [9.67 ppg], is 1593.28 m [5225.96 ft] less than the limit when the collapse period is not considered. [ABSTRACT FROM AUTHOR]

Tight sandstone reservoirs are significant sources of natural gas reserves. As traditional reserves become increasingly scarce and costly, optimizing the development of these reservoirs becomes crucial. This study introduces a novel two-phase gas–water flow model for single wells, incorporating both Darcy and non-Darcy flow equations. These equations are derived from mass conservation and momentum principles for both gas and water phases. Using data from a real tight gas well, our model, which includes stress-sensitive phases for gas and water, outperforms traditional Darcy flow models. Specifically, the average relative deviations in daily production rates were 0.1815% for gas and − 0.2677% for water, which are significantly smaller compared to traditional Darcy flow models. Further application of the non-Darcy flow model reveals strategies to enhance well performance. For example, mitigating liquid lock damage within a 2 m radius near the well could restore the permeability from 0.045 to 0.143 mD, thereby tripling the daily gas production. This non-Darcy flow model is easy to implement and shows significant potential in forecasting production yields in tight sandstone reservoirs, highlighting its importance in the petroleum and natural gas industry. [ABSTRACT FROM AUTHOR]

Legal documents, like contracts or laws, are subject to interpretation. Different people can have different interpretations of the very same document. Large parts of judicial branches all over the world are concerned with settling disagreements that arise, in part, from these different interpretations. In this context, it only seems natural that during the annotation of legal machine learning data sets, disagreement, how to report it, and how to handle it should play an important role. This article presents an analysis of the current state-of-the-art in the annotation of legal machine learning data sets. The results of the analysis show that all of the analysed data sets remove all traces of disagreement, instead of trying to utilise the information that might be contained in conflicting annotations. Additionally, the publications introducing the data sets often do provide little information about the process that derives the "gold standard" from the initial annotations, often making it difficult to judge the reliability of the annotation process. Based on the state-of-the-art, the article provides easily implementable suggestions on how to improve the handling and reporting of disagreement in the annotation of legal machine learning data sets. [ABSTRACT FROM AUTHOR]

Additive friction stir deposition (AFSD) is a solid-state additive manufacturing method that exploits frictional heat generation and severe plastic deformation to achieve metallurgical bonding during layer-by-layer deposition. AFSD can be used for additive manufacturing of bulk components or repair of aluminum alloys as the sub-solidus processing temperatures can be beneficial over fusion-based alternatives. Due to dynamic recrystallization during AFSD processing, significant evolution of the microstructure can occur which can lead to substantial gradients in grain and intermetallic particle size. In this study, we present a history dependent modeling framework to predict the microstructure evolution in the AFSD process through mesh-free numerical simulations. In this work, experimentally quantified relationships between grain and intermetallic particle size as well as temperatures and strain rates were incorporated into a smooth particle hydrodynamic simulation framework to predict the microstructure after AFSD processing. The SPH simulation approach showed reasonable agreement between the model predictions and experimental results of grain and intermetallic particle size distribution after AFSD processing. [ABSTRACT FROM AUTHOR]

Autonomous vehicles have limited computational resources and thus require efficient control systems. The cost and size of sensors have limited the development of self-driving cars. To overcome these restrictions, this study proposes an efficient framework for the operation of vision-based automatic vehicles; the framework requires only a monocular camera and a few inexpensive radars. The proposed algorithm comprises a multi-task UNet (MTUNet) network for extracting image features and constrained iterative linear quadratic regulator (CILQR) and vision predictive control (VPC) modules for rapid motion planning and control. MTUNet is designed to simultaneously solve lane line segmentation, the ego vehicle's heading angle regression, road type classification, and traffic object detection tasks at approximately 40 FPS for 228 × 228 pixel RGB input images. The CILQR controllers then use the MTUNet outputs and radar data as inputs to produce driving commands for lateral and longitudinal vehicle guidance within only 1 ms. In particular, the VPC algorithm is included to reduce steering command latency to below actuator latency, preventing performance degradation during tight turns. The VPC algorithm uses road curvature data from MTUNet to estimate the appropriate correction for the current steering angle at a look-ahead point to adjust the turning amount. The inclusion of the VPC algorithm in a VPC-CILQR controller leads to higher performance on curvy roads than the use of CILQR alone. Our experiments demonstrate that the proposed autonomous driving system, which does not require high-definition maps, can be applied in current autonomous vehicles. [ABSTRACT FROM AUTHOR]

Furnace temperature and oxygen content are important parameters reflecting the combustion inside a circulating fluidized bed (CFB) boiler. Accurately predicting boiler output is a complex task due to the high noise and nonsmoothness of actual boiler input and output data. In this paper, a new hybrid convolutional neural network (CNN), bidirectional long short-term memory (biLSTM) network, and squeezing and excitation (SE) network prediction model is proposed to significantly improve the prediction accuracy of oxygen content and furnace temperature by combining the advantages of multiple deep learning networks. This network can extract spatiotemporal characteristics of input parameters such as coal feed to effectively predict boiler furnace temperature and oxygen content. CNNs can extract complex features such as dynamic and static nonlinearities between multiple variables affecting the furnace temperature and oxygen content, as well as high noise. The biLSTM network layer can efficiently handle the temporal information of irregular trends in modeling time series components; SE can extract the important information between channels through the feature relationships between channels for better overfeature extraction. The CNN-biLSTM-SE model can effectively solve the problem of nonlinear mapping complexity between inputs and outputs. Experiments show that the proposed CNN-biLSTM-SE model outperforms existing methods. The experimental results showed that the average MAPE errors for oxygen content prediction were CNN-biLSTM-SE (0.038), CNN-biLSTM with attention mechanism (AM) (0.043), CNN-biLSTM (0.051), CNN-LSTM (0.051), biLSTM (0.051), RNN (0.051), LSTM(0.0052), and CNN(0.0054). Extensive experiments in CFB boilers with oxygen content and furnace temperature show that the proposed CNN-biLSTM-SE model achieves better results in terms of goodness-of-fit, generalization ability and accuracy. [ABSTRACT FROM AUTHOR]

Multi-label text classification (MLTC) aims to assign one or more labels to each document. Previous studies mainly use the label co-occurrence matrix obtained from the training set to establish the correlation between labels, but this approach ignores the noise in label co-occurrence, and applies the ungeneralizable label co-occurrence relationship to model testing and validation. In addition, labelling co-occurrence relationship globally lacks attention to a specific document, which results in the loss of the local label co-occurrence relationship. To address this issue, we introduced a new multi-label text classification model in this study, presenting CoocNet, which adopts a two-step label detection to effectively tackle the challenge of modeling label co-occurrence relations. The model first captures the global co-occurrence relationships of labels using the label co-occurrence matrix and denoises the label noise through the label denoising attention mechanism, and then uses a contrast learning strategy to capture the local label co-occurrence relationships among specific different documents. In particular, we unify the co-occurrence labeling into an auxiliary training task that runs parallel to the multi-label classification task. The new task supervises the learning of sentence representations for documents by leveraging the modeled label co-occurrence relationships, enhancing the model's generalization ability. Another novelty is that the auxiliary task is only active during model training, thereby preventing label co-occurrence relationships from interfering with the model's predictions outside the training phase. The experimental results on three benchmark datasets (Reuters-21578, AAPD, and RCV1) demonstrate that our model outperforms the existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Introduction: A dynamic molecular biomarker that can identify early efficacy of immune checkpoint inhibitor (ICI) therapy remains an unmet clinical need. Here we evaluate if a novel circulating tumor DNA (ctDNA) assay, xM, used for treatment response monitoring (TRM), that quantifies changes in ctDNA tumor fraction (TF), can predict outcome benefits in patients treated with ICI alone or in combination with chemotherapy in a real-world (RW) cohort. Methods: This retrospective study consisted of patients with advanced cancer from the Tempus de-identified clinical genomic database who received longitudinal liquid-based next-generation sequencing. Eligible patients had a blood sample ≤ 40 days prior to the start of ICI initiation and an on-treatment blood sample 15–180 days post ICI initiation. TF was calculated via an ensemble algorithm that utilizes TF estimates derived from variants and copy number information. Patients with molecular response (MR) were defined as patients with a ≥ 50% decrease in TF between tests. In the subset of patients with rw-imaging data between 2 and 18 weeks of ICI initiation, the predictive value of MR in addition to rw-imaging was compared to a model of rw-imaging alone. Results: The evaluable cohort (N = 86) was composed of 14 solid cancer types. Patients received either ICI monotherapy (38.4%, N = 33) or ICI in combination with chemotherapy (61.6%, N = 53). Patients with MR had significantly longer rw-overall survival (rwOS) (hazard ratio (HR) 0.4, P = 0.004) and rw-progression free survival (rwPFS) (HR 0.4, P = 0.005) than patients with molecular non-response (nMR). Similar results were seen in the ICI monotherapy subcohort; HR 0.2, P = 0.02 for rwOS and HR 0.2, P = 0.01 for rwPFS. In the subset of patients with matched rw-imaging data (N = 51), a model incorporating both MR and rw-imaging was superior in predicting rwOS than rw-imaging alone (P = 0.02). Conclusions: xM used for TRM is a novel serial quantitative TF algorithm that can be used clinically to evaluate ICI therapy efficacy. [ABSTRACT FROM AUTHOR]