Improve Prediction Performance Research Articles

Attention-Oriented CNN Method for Type 2 Diabetes Prediction

Diabetes is caused by insulin deficiency or impaired biological action, and long-term hyperglycemia leads to a variety of tissue damage and dysfunction. Therefore, the early prediction of diabetes and timely intervention and treatment are crucial. This paper proposes a robust framework for the prediction and diagnosis of type 2 diabetes (T2DM) to aid in diabetes applications in clinical diagnosis. The data-preprocessing stage includes steps such as outlier removal, missing value filling, data standardization, and assigning class weights to ensure the quality and consistency of the data, thereby improving the performance and stability of the model. This experiment used the National Health and Nutrition Examination Survey (NHANES) dataset and the publicly available PIMA Indian dataset (PID). For T2DM classification, we designed a convolutional neural network (CNN) and proposed a novel attention-oriented convolutional neural network (SECNN) through the channel attention mechanism. To optimize the hyperparameters of the model, we used grid search and K-fold cross-validation methods. In addition, we also comparatively analyzed various machine learning (ML) models such as support vector machine (SVM), logistic regression (LR), decision tree (DT), random forest (RF), and artificial neural network (ANN). Finally, we evaluated the performance of the model using performance evaluation metrics such as precision, recall, F1-Score, accuracy, and AUC. Experimental results show that the SECNN model has an accuracy of 94.12% on the NHANES dataset and an accuracy of 89.47% on the PIMA Indian dataset. SECNN models and CNN models show significant improvements in diabetes prediction performance compared to traditional ML models. The comparative analysis of the SECNN model and the CNN model has significantly improved performance, further verifying the advantages of introducing the channel attention mechanism. The robust diabetes prediction framework proposed in this article establishes an effective foundation for diabetes diagnosis and prediction, and has a positive impact on the development of health management and medical industries.

Enhancing geospatial prediction models with feature engineering from road networks: a graph-driven approach

Traditional geospatial predictive models for property valuation have naturally relied on coordinates as well as ‘hedonic’ (internal and external) features. In particular, location-centric methods such as Geographically Weighted Regression (GWR) and Kriging have focused on intrinsic target characteristics together with distances between individual targets. However, especially in the context of heavily urbanized areas, these approaches might overlook crucial aspects arising from the underlying topological structure that presents itself in such areas. Concretely, in this work, we focus on the structure arising from the road network connecting properties. We introduce a novel though straightforward technique for feature engineering based on graphs constructed on a road network. We then extract relevant features from these and utilize those as inputs for predictive models and assess their performance benefits when used together with a variety of both well-known geospatial models and state-of-art machine learning models. To this end, we present an exhaustive experiment using four different real-life data sets across various regions and exhibiting sizes outperforming many comparative works in the field. Our findings reveal that our feature engineering approach offers significant improvements in predictive performance. Finally, we apply Shapley values as an interpretability technique to confirm the reliability and effectiveness of our approach.

Sampling-based novel heterogeneous multi-layer stacking ensemble method for telecom customer churn prediction

In recent times, customer churn has become one of the most significant issues in business-oriented sectors with telecommunication being no exception. Maintaining current customers is particularly valuable due to the high degree of rivalry among telecommunication companies and the costs of acquiring new ones. The early prediction of churned customers may help telecommunication companies to identify the causes of churn and design industrial tactics to address or mitigate the churn problem. Controlling customer churn by developing efficient and reliable customer churn prediction (CCP) solutions is essential to achieving this objective. Findings from existing CCP studies have shown that numerous methods, such as rule-based and machine-learning (ML) mechanisms, have been devised to solve the CCP problem. Nonetheless, the problems of adaptability and the resilience of rule-based CCP solutions are its major weaknesses, and the skewed pattern of churn datasets (class imbalance) is detrimental to the prediction performances of conventional ML models in CCP. Hence, this research developed a robust heterogeneous multi-layer stacking ensemble method (HMSE) for effective CCP. Specifically, in the HMSE method, the prediction prowess of five ML classifiers (Random Forest (RF), Bayesian network (BN), Support Vector Machine (SVM), K-Nearest Neighbour (KNN), and Repeated Incremental Pruning to Produce Error Reduction (RIPPER)) with distinct computational characteristics are ensembled based on stacking and the resulting model is further enhanced using a forest penalizing attribute (FPA) model. The synthetic minority oversampling technique (SMOTE) is integrated with the proposed HMSE to balance the skewed class label present in the original experimental datasets. Extensive tests were carried out to determine the effectiveness of the proposed HMSE and S-HMSE on standard telecom CCP datasets. Observed findings from the experimental results showed that HMSE and S-HMSE can effectively predict churners even with the class imbalance (skewed datasets) problem. In addition, comparison studies demonstrated that the suggested S-HMSE offered improved prediction performance and optimum solutions for CCP in the telecom sector in comparison with baseline classifiers, homogeneous ensemble methods, and current CCP approaches.

Molecular property prediction based on graph structure learning.

Molecular property prediction (MPP) is a fundamental but challenging task in the computer-aided drug discovery process. More and more recent works employ different graph-based models for MPP, which have achieved considerable progress in improving prediction performance. However, current models often ignore relationships between molecules, which could be also helpful for MPP. For this sake, in this article we propose a graph structure learning (GSL) based MPP approach, called GSL-MPP. Specifically, we first apply graph neural network (GNN) over molecular graphs to extract molecular representations. Then, with molecular fingerprints, we construct a molecule similarity graph (MSG). Following that, we conduct GSL on the MSG, i.e. molecule-level GSL, to get the final molecular embeddings, which are the results of fuzing both GNN encoded molecular representations and the relationships among molecules. That is, combining both intra-molecule and inter-molecule information. Finally, we use these molecular embeddings to perform MPP. Extensive experiments on 10 various benchmark datasets show that our method could achieve state-of-the-art performance in most cases, especially on classification tasks. Further visualization studies also demonstrate the good molecular representations of our method. Source code is available at https://github.com/zby961104/GSL-MPP.

Just-in-Time crash prediction for mobile apps

Just-In-Time (JIT) defect prediction aims to identify defects early, at commit time. Hence, developers can take precautions to avoid defects when the code changes are still fresh in their minds. However, the utility of JIT defect prediction has not been investigated in relation to crashes of mobile apps. We therefore conducted a multi-case study employing both quantitative and qualitative analysis. In the quantitative analysis, we used machine learning techniques for prediction. We collected 113 reliability-related metrics for about 30,000 commits from 14 Android apps and selected 14 important metrics for prediction. We found that both standard JIT metrics and static analysis warnings are important for JIT prediction of mobile app crashes. We further optimized prediction performance, comparing seven state-of-the-art defect prediction techniques with hyperparameter optimization. Our results showed that Random Forest is the best performing model with an AUC-ROC of 0.83. In our qualitative analysis, we manually analysed a sample of 642 commits and identified different types of changes that are common in crash-inducing commits. We explored whether different aspects of changes can be used as metrics in JIT models to improve prediction performance. We found these metrics improve the prediction performance significantly. Hence, we suggest considering static analysis warnings and Android-specific metrics to adapt standard JIT defect prediction models for a mobile context to predict crashes. Finally, we provide recommendations to bridge the gap between research and practice and point to opportunities for future research.

Predicting the Intensity of Tropical Cyclones over the Western North Pacific Using a Dual-Branch Spatiotemporal Attention Convolutional Network

Abstract This paper proposes a spatiotemporal attention convolutional network (STAC-Pred) that leverages deep learning techniques to model the spatiotemporal features of tropical cyclones (TCs) and enable real-time prediction of their intensity. The proposed model employs dual branches to concurrently extract and integrate features from intensity heatmaps and satellite cloud imagery. Additionally, a residual attention (RA) module is integrated into the three-channel cloud imagery convolution process to automatically respond to high wind speed regions. TC’s longitude, latitude, and radius of winds are injected into the multi-timepoint prediction model to assist in the prediction task. Furthermore, a rolling mechanism (RM) is employed to smooth the fluctuation of losses, achieving accurate prediction of TC intensity. We use several TC records to evaluate and validate the universality and effectiveness of the model. The results indicate that STAC-Pred achieves satisfactory performance. Specifically, the STAC-Pred model improves prediction performance by 47.69% and 28.26% compared to the baseline (official institutions) at 3- and 6-h intervals, respectively. Significance Statement Tropical cyclones are one of the most deadly and damaging natural disasters in coastal areas worldwide. Early prediction can significantly reduce casualties and property losses. This study innovatively conducts dimensionality augmentation on one-dimensional intensity numerical sequences and proposes a new network model for rolling forecast of their future intensity. The proposed prototype model (not yet incorporating any atmospheric conditions) shows promising results for 3- and 6-h advance forecasts, providing valuable guidance for forecasters regarding real-time operational predictions of short-term tropical cyclone intensity.

Water vapor content prediction based on neural network model selection and optimal fusion

Accurately predicting the evolution of water vapor content has significant practical engineering implications for accurately determining the timing of artificial rain enhancement operations. However, the nonlinear, unstable, and chaotic nature of water vapor content presents considerable challenges to its precise prediction. To address this, our research proposes a combined prediction model, based on a neural network model selection mechanism and small sample water vapor content data observed by microwave radiometers in the Zhengzhou area. This combined model utilizes seven neural network models as candidate models and dynamically selects the optimal three models as the central prediction components via evaluation indicators. Additionally, we employ the maximum information coefficient method to preserve the optimal input features and use a time-varying rate wave mode decomposition algorithm as the front-end processing module. This module processes the original water vapor content sequence and extracts relevant latent information. Finally, we incorporate the African vulture intelligent optimization algorithm as the backend processing component to optimize the weighted combination coefficients, achieving the integration of prediction results. Experimental results reveal that the Mean Absolute Percentage Errors (MAPE) of the proposed model on three types of water vapor content datasets are 0.208%, 0.876%, and 0.369%, respectively. This suggests a predictive performance improvement of at least 10% compared to existing models. The prediction model proposed in this study not only establishes an accurate and reliable mechanism for predicting water vapor content but also offers more comprehensive decision support information for weather modification operations.

LMCrot: an enhanced protein crotonylation site predictor by leveraging an interpretable window-level embedding from a transformer-based protein language model.

Recent advancements in natural language processing have highlighted the effectiveness of global contextualized representations from protein language models (pLMs) in numerous downstream tasks. Nonetheless, strategies to encode the site-of-interest leveraging pLMs for per-residue prediction tasks, such as crotonylation (Kcr) prediction, remain largely uncharted. Herein, we adopt a range of approaches for utilizing pLMs by experimenting with different input sequence types (full-length protein sequence versus window sequence), assessing the implications of utilizing per-residue embedding of the site-of-interest as well as embeddings of window residues centered around it. Building upon these insights, we developed a novel residual ConvBiLSTM network designed to process window-level embeddings of the site-of-interest generated by the ProtT5-XL-UniRef50 pLM using full-length sequences as input. This model, termed T5ResConvBiLSTM, surpasses existing state-of-the-art Kcr predictors in performance across three diverse datasets. To validate our approach of utilizing full sequence-based window-level embeddings, we also delved into the interpretability of ProtT5-derived embedding tensors in two ways: firstly, by scrutinizing the attention weights obtained from the transformer's encoder block; and secondly, by computing SHAP values for these tensors, providing a model-agnostic interpretation of the prediction results. Additionally, we enhance the latent representation of ProtT5 by incorporating two additional local representations, one derived from amino acid properties and the other from supervised embedding layer, through an intermediate fusion stacked generalization approach, using an n-mer window sequence (or, peptide/fragment). The resultant stacked model, dubbed LMCrot, exhibits a more pronounced improvement in predictive performance across the tested datasets. LMCrot is publicly available at https://github.com/KCLabMTU/LMCrot.

Improved training framework in a neural network model for disruption prediction and its application on EXL-50

A neural network model with a classical annotation method has been used on the EXL-50 tokamak to predict impending disruption. However, the results revealed issues of overfitting and overconfidence in predictions caused by inaccurate labeling. To mitigate these issues, an improved training framework has been proposed. In this approach, soft labels from previous training serve as teachers to supervise the further learning process; this has lead to a significant improvement in predictive model performance. Notably, this enhancement is primarily attributed to the coupling effect of the soft labels and correction mechanism. This improved training framework introduces an instance-specific label smoothing method, which reflects a more nuanced model assessment on the likelihood of a disruption. It presents a possible solution to effectively address the challenges associated with accurate labeling across different machines.

Cross-Project Defect Prediction Based on Domain Adaptation and LSTM Optimization

Cross-project defect prediction (CPDP) aims to predict software defects in a target project domain by leveraging information from different source project domains, allowing testers to identify defective modules quickly. However, CPDP models often underperform due to different data distributions between source and target domains, class imbalances, and the presence of noisy and irrelevant instances in both source and target projects. Additionally, standard features often fail to capture sufficient semantic and contextual information from the source project, leading to poor prediction performance in the target project. To address these challenges, this research proposes Smote Correlation and Attention Gated recurrent unit based Long Short-Term Memory optimization (SCAG-LSTM), which first employs a novel hybrid technique that extends the synthetic minority over-sampling technique (SMOTE) with edited nearest neighbors (ENN) to rebalance class distributions and mitigate the issues caused by noisy and irrelevant instances in both source and target domains. Furthermore, correlation-based feature selection (CFS) with best-first search (BFS) is utilized to identify and select the most important features, aiming to reduce the differences in data distribution among projects. Additionally, SCAG-LSTM integrates bidirectional gated recurrent unit (Bi-GRU) and bidirectional long short-term memory (Bi-LSTM) networks to enhance the effectiveness of the long short-term memory (LSTM) model. These components efficiently capture semantic and contextual information as well as dependencies within the data, leading to more accurate predictions. Moreover, an attention mechanism is incorporated into the model to focus on key features, further improving prediction performance. Experiments are conducted on apache_lucene, equinox, eclipse_jdt_core, eclipse_pde_ui, and mylyn (AEEEM) and predictor models in software engineering (PROMISE) datasets and compared with active learning-based method (ALTRA), multi-source-based cross-project defect prediction method (MSCPDP), the two-phase feature importance amplification method (TFIA) on AEEEM and the two-phase transfer learning method (TPTL), domain adaptive kernel twin support vector machines method (DA-KTSVMO), and generative adversarial long-short term memory neural networks method (GB-CPDP) on PROMISE datasets. The results demonstrate that the proposed SCAG-LSTM model enhances the baseline models by 33.03%, 29.15% and 1.48% in terms of F1-measure and by 16.32%, 34.41% and 3.59% in terms of Area Under the Curve (AUC) on the AEEEM dataset, while on the PROMISE dataset it enhances the baseline models’ F1-measure by 42.60%, 32.00% and 25.10% and AUC by 34.90%, 27.80% and 12.96%. These findings suggest that the proposed model exhibits strong predictive performance.

Development and validation of a nomogram for predicting 28-day mortality in patients with ischemic stroke.

We aimed to construct a validated nomogram model for predicting short-term (28-day) ischemic stroke mortality among critically ill populations. We collected raw data from the Medical Information Mart for Intensive Care IV database, a comprehensive repository renowned for its depth and breadth in critical care information. Subsequently, a rigorous analytical framework was employed, incorporating a 10-fold cross-validation procedure to ensure robustness and reliability. Leveraging advanced statistical methodologies, specifically the least absolute shrinkage and selection operator regression, variables pertinent to 28-day mortality in ischemic stroke were meticulously screened. Next, binary logistic regression was utilized to establish nomogram, then applied concordance index to evaluate discrimination of the prediction models. Predictive performance of the nomogram was assessed by integrated discrimination improvement (IDI) and net reclassification index (NRI). Additionally, we generated calibration curves to assess calibrating ability. Finally, we evaluated the nomogram's net clinical benefit using decision curve analysis (DCA), in comparison with scoring systems clinically applied under common conditions. A total of 2089 individuals were identified and assigned into training (n = 1443) or validation (n = 646) cohorts. Various identified risk factors, including age, ethnicity, marital status, underlying metastatic solid tumor, Charlson comorbidity index, heart rate, Glasgow coma scale, glucose concentrations, white blood cells, sodium concentrations, potassium concentrations, mechanical ventilation, use of heparin and mannitol, were associated with short-term (28-day) mortality in ischemic stroke individuals. A concordance index of 0.834 was obtained in the training dataset, indicating that our nomogram had good discriminating ability. Results of IDI and NRI in both cohorts proved that our nomogram had positive improvement of predictive performance, compared to other scoring systems. The actual and predicted incidence of mortality showed favorable concordance on calibration curves (P > 0.05). DCA curves revealed that, compared with scoring systems clinically used under common conditions, the constructed nomogram yielded a greater net clinical benefit. Utilizing a comprehensive array of fourteen readily accessible variables, a prognostic nomogram was meticulously formulated and rigorously validated to provide precise prognostication of short-term mortality within the ischemic stroke cohort.

Requirement Dependency Extraction Based on Improved Stacking Ensemble Machine Learning

To address the cost and efficiency issues of manually analysing requirement dependency in requirements engineering, a requirement dependency extraction method based on part-of-speech features and an improved stacking ensemble learning model (P-Stacking) is proposed. Firstly, to overcome the problem of singularity in the feature extraction process, this paper integrates part-of-speech features, TF-IDF features, and Word2Vec features during the feature selection stage. The particle swarm optimization algorithm is used to allocate weights to part-of-speech tags, which enhances the significance of crucial information in requirement texts. Secondly, to overcome the performance limitations of standalone machine learning models, an improved stacking model is proposed. The Low Correlation Algorithm and Grid Search Algorithms are utilized in P-stacking to automatically select the optimal combination of the base models, which reduces manual intervention and improves prediction performance. The experimental results show that compared with the method based on TF-IDF features, the highest F1 scores of a standalone machine learning model in the three datasets were improved by 3.89%, 10.68%, and 21.4%, respectively, after integrating part-of-speech features and Word2Vec features. Compared with the method based on a standalone machine learning model, the improved stacking ensemble machine learning model improved F1 scores by 2.29%, 5.18%, and 7.47% in the testing and evaluation of three datasets, respectively.

Comprehensive transferability assessment of short-term cross-building-energy prediction using deep adversarial network transfer learning

Data-driven models are widely used for building-energy predictions (BEPs). In practice, these models may fail when the available data on the target building is insufficient. Transfer learning (TL), where useful knowledge from information-rich source buildings with sufficient data is learned to enhance the prediction of information-poor buildings with data shortages, can address the problem of poor prediction performance caused by insufficient data. However, an important issue is finding suitable information-rich buildings to maximize the advantages of TL in cross- BEP. To address this issue, this study explored the selection of source buildings from three perspectives: building-energy data similarity between source and target buildings, building information characteristics, and the volume of training data. The impact of these three factors on the performance improvement of cross- BEP was assessed in a data-centric manner. Based on our previous studies, we selected a deep adversarial neural network (DANN) as the TL strategy for cross-BEP and systematically investigated the performance improvement and transferability of DANN from multiple perspectives of both post-hoc and ex-ante analysis. The Building Data Genome Project datasets were used for validation. Thirty-six buildings of six types and 180 source-target building pairs were considered. Our results demonstrated that DANN could effectively improve model performance by 40–90 % and 20%–80 % compared to non-optimized LSTM and parameter-optimized LSTM. When the same type and location source-target building pairs were only considered, the DTW index showed a relative strong negative linear correlation with the DANN prediction performance improvement, and the goodness of fitting is around 0.80. For building energy data within one year considered, DANN should be trained using no less than 6-month source domain data and no more than 4-week target domain data to improve transferability and reduce the cross-building energy prediction error.

Wave excitation force prediction for arrays of wave energy converters in directional waves

The implementation of advanced control strategies is an effective means of maximizing the energy production of wave energy converters (WECs), and most of them require future wave excitation forces to determine the optimal control sequence. The WECs deployed in arrays can enable a significant reduction in the cost of wave energy and improve prediction performance by incorporating excitation forces from the array. In this paper, a critical comparison of the excitation prediction methods, including the time series, machine learning, and neural network, for a two-body heaving point absorber WEC is presented. Considering the symmetry of the WEC and arrays, the directional spectrum is utilized to determine the reference measurement of wave excitation. The prediction methods are applied to isolated WEC and different array layouts. Moreover, additional sensitivity analyses are performed to evaluate the performance. The results show that the autoregressive with extra input (ARX) model has the best performance in short-term wave excitation force prediction. In most cases, the ARX model is weakly influenced by the sampling period and can adapt well to changes in the directional distribution and sea states of irregular waves, and the ARX model requires the least amount of computational time in the simulations.

Forecasting train arrival delays on the Ankara – Eskişehir high-speed line in Turkey

Railway operations may experience delays due to technical issues or weather conditions. Accurate prediction of such delays can enhance the quality of rail transport services and the effectiveness of railway operations. The study has developed the arrival delay prediction model using random forest regression based on the train operation data from the Ankara - Eskişehir high-speed train line in Turkey. The model can simultaneously predict arrival delays at all downstream stations on this line and continuously update these predictions as new information about train movements becomes available. The accuracy rates of the model vary from 76% to 99% under a 1-min prediction error. The results show that incorporating variables related to weather conditions and technical problems related to train control systems into the model improves prediction performance. The contribution of these variables to the model performance increases as the prediction horizon widens. The model results suggest that the model predictions may assist network managers in making better decisions about train operations. In order to evaluate the model's performance from the passengers' point of view, the study has proposed two methods: the proportion of late predictions and the stability of forecasts. The findings indicate that most trains (between 96.7% and 99%) have stable arrival delay predictions at target stations. The proportion of 2-min (or greater) late predictions, which means that the predicted delay exceeds the actual delay by 2 min or more, fluctuates from 14% to 0.5%, depending on the prediction horizon. Although the ratio for the short horizons (one station ahead) becomes relatively low, it is necessary to be cautious when using the model predictions to inform passengers because a prediction of more than 1 min late for short horizons might have negative consequences (e.g., misleading passengers to leave stations).

Predictive model for a product without history using LightGBM. Pricing model for a new product

The article focuses on developing a predictive product pricing model using LightGBM. Also, the goal was to adapt the LightGBM method for regression problems and, especially, in the problems of forecasting the price of a product without history, that is, with a cold start.The article contains the necessary concepts to understand the working principles of the light gradient boosting machine, such as decision trees, boosting, random forests, gradient descent, GBM (Gradient Boosting Machine), GBDT (Gradient Boosting Decision Trees). The article provides detailed insights into the algorithms used for identifying split points, with a focus on the histogram-based approach.LightGBM enhances the gradient boosting algorithm by introducing an automated feature selection mechanism and giving special attention to boosting instances characterized by more substantial gradients. This can lead to significantly faster training and improved prediction performance. The Gradient-based One-Side Sampling (GOSS) and Exclusive Feature Bundling (EFB) techniques used as enhancements to LightGBM are vividly described. The article presents the algorithms for both techniques and the complete LightGBM algorithm.This work contains an experimental result. To test the lightGBM, a real dataset of one Japanese C2C marketplace from the Kaggle site was taken. In the practical part, a performance comparison between LightGBM and XGBoost (Extreme Gradient Boosting Machine) was performed. As a result, only a slight increase in estimation performance (RMSE, MAE, R-squard) was found by applying LightGBM over XGBoost, however, there exists a notable contrast in the training procedure’s time efficiency. LightGBM exhibits an almost threefold increase in speed compared to XGBoost, making it a superior choice for handling extensive datasets.This article is dedicated to the development and implementation of machine learning models for product pricing using LightGBM. The incorporation of automatic feature selection, a focus on highgradient examples, and techniques like GOSS and EFB demonstrate the model’s versatility and efficiency. Such predictive models will help companies improve their pricing models for a new product. The speed of obtaining a forecast for each element of the database is extremely relevant at a time of rapid data accumulation.

Construction and Analysis of QPSO-LSTM Model in Network Security Situation Prediction

The continuous improvement of artificial intelligence technology has deepened its application in many fields and provided more support for predicting network security situations. QPSO-LSTM model based on LSTM neural network and fused with QPSO algorithm provides more options for improving network security situation prediction, further enhancing the effectiveness of network security situation prediction, and enabling more efficient and accurate prediction and analysis of network security situations. By comparing the applications of different types of algorithms in network security situation prediction, it was found that the QPSO-LSTM model has smaller prediction errors, can achieve higher prediction accuracy, and can also obtain higher F1-score and AUC values; the shorter identifying runtime also lays the foundation for improving the speed and efficiency of network security situation prediction. Therefore, in the field of network security situation prediction, the application of QPSO-LSTM model can provide more support for further improvement and improvement of security situation prediction performance in this field.

Prediction of small-scale leak flow rate in LOCA situations using bidirectional GRU

It is difficult to detect a small-scale leakage in a nuclear power plant (NPP) quickly and take appropriate action. Delaying these procedures can have adverse effects on NPPs. In this paper, we propose leak flow rate prediction using the bidirectional gated recurrent unit (Bi-GRU) method to detect leakage quickly and accurately in small-scale leakage situations because large-scale leak rates are known to be predicted accurately. The data were acquired by simulating small loss-of-coolant accidents (LOCA) or small-scale leakage situations using the modular accident analysis program (MAAP) code. In addition, to improve prediction performance, data were collected by distinguishing the break sizes in more detail. In addition, the prediction accuracy was improved by performing both LOCA diagnosis and leak flow rate prediction in small LOCA situations. The prediction model developed using the Bi-GRU showed a superior prediction performance compared with other artificial intelligence methods. Accordingly, the accurate and effective prediction model for small-scale leakage situations proposed herein is expected to support operators in decision-making and taking actions.

Large‐scale breeding applications of unoccupied aircraft systems enabled genomic prediction

AbstractBreeding for improved, reliable cultivars despite growing environmental irregularity can be challenging. Unoccupied aircraft systems (UAS) are a popular high‐throughput phenotyping technology that has been shown to help interpret the mechanisms associated with crop productivity and environmental response, creating potential for improved breeding strategies. Spectral reflectance indices (SRIs), encompassing both vegetation and water indices like normalized difference vegetation index (NDVI), normalized difference red‐edge index, and normalized water index, were employed to assess 4094 winter wheat genotypes across 11,593 breeding plots at Washington State University from 2019 through 2022. SRIs were then used with genomic data in univariate models as covariates and multivariate models as secondary response variables for predictions of grain yield. The prediction accuracy of models was evaluated using a leave‐one‐year‐out validation strategy against a base genomic prediction method. Including SRI data as fixed effects in univariate genomic prediction models can improve prediction accuracy over the control but is unreliable across years. When used in multivariate models, SRIs improve prediction performance across years but require high‐performance computational resources that could limit feasibility. In univariate models, when test year NDVI data were available and used to calculate breeding values, prediction performance was at least 16% better than the control, ranging in prediction accuracy from 0.54 in 2019 to 0.93 in 2020. This study highlights the limited reliability of SRI use in genomic prediction of untested environments and locations. However, a significant application for the technology can be found in early‐season UAS data collection to aid accurate predictions in late season, a helpful tool in tight turnaround times commonly experienced in winter crop breeding programs.

Dynamic radiomics based on contrast-enhanced MRI for predicting microvascular invasion in hepatocellular carcinoma

ObjectiveTo exploit the improved prediction performance based on dynamic contrast-enhanced (DCE) MRI by using dynamic radiomics for microvascular invasion (MVI) in hepatocellular carcinoma (HCC).MethodsWe retrospectively included 175 and 75 HCC patients who underwent preoperative DCE-MRI from September 2019 to August 2022 in institution 1 (development cohort) and institution 2 (validation cohort), respectively. Static radiomics features were extracted from the mask, arterial, portal venous, and equilibrium phase images and used to construct dynamic features. The static, dynamic, and dynamic–static radiomics (SR, DR, and DSR) signatures were separately constructed based on the feature selection method of LASSO and classification algorithm of logistic regression. The receiver operating characteristic (ROC) curves and the area under the curve (AUC) were plotted to evaluate and compare the predictive performance of each signature.ResultsIn the three radiomics signatures, the DSR signature performed the best. The AUCs of the SR, DR, and DSR signatures in the training set were 0.750, 0.751 and 0.805, respectively, while in the external validation set, the corresponding AUCs were 0.706, 0756 and 0.777. The DSR signature showed significant improvement over the SR signature in predicting MVI status (training cohort: P = 0.019; validation cohort: P = 0.044). After external validation, the AUC value of the SR signature decreased from 0.750 to 0.706, while the AUC value of the DR signature did not show a decline (AUCs: 0.756 vs. 0.751).ConclusionsThe dynamic radiomics had an improved effect on the MVI prediction in HCC, compared with the static DCE MRI-based radiomics models.