Hierarchical Time-Series Approaches for Photovoltaic System Performance Forecasting With Sparse Datasets

Acute kidney injury (AKI) is a common postoperative complication among patients in the neurological intensive care unit (NICU), often resulting in poor prognosis and high mortality. In this retrospective cohort study, we established a model for predicting AKI following brain surgery based on an ensemble machine learning algorithm using data from 582 postoperative patients admitted to the NICU at the Dongyang People's Hospital from March 1, 2017, to January 31, 2020. Demographic, clinical, and intraoperative data were collected. Four machine learning algorithms (C5.0, support vector machine, Bayes, and XGBoost) were used to develop the ensemble algorithm. The AKI incidence in critically ill patients after brain surgery was 20.8%. Intraoperative blood pressure; postoperative oxygenation index; oxygen saturation; and creatinine, albumin, urea, and calcium levels were associated with the postoperative AKI occurrence. The area under the curve value for the ensembled model was 0.85. The accuracy, precision, specificity, recall, and balanced accuracy values were 0.81, 0.86, 0.44, 0.91, and 0.68, respectively, indicating good predictive ability. Ultimately, the models using perioperative variables exhibited good discriminatory ability for early prediction of postoperative AKI risk in patients admitted to the NICU. Thus, the ensemble machine learning algorithm may be a valuable tool for forecasting AKI.

Background: Cardiac arrest (CA) poses a significant risk of death and long-term neurological disability yet there remains a lack of accurate and reliable methods to prognosticate post-CA outcome, indicating a major unmet need. Additionally, no existing CA outcome prediction model utilizes physiological time series (PTS) data, which captures transitions in a patient’s health state at high temporal resolution. Materials and Methods: We screened the Philips eICU database, which includes over 200,000 patients in 200 hospitals, extracting data on CA patients within 24 hours of ICU admission. We first extracted PTS and Electronic Health Record (HER) features and selected our features using nested Random Forest. The outcome labels were neurological state or mortality at ICU discharge. We tested various individual and ensemble machine learning algorithms (GLM, Random Forest, Gradient Boosting, Support Vector Machine, Neural Networks) and optimization techniques (hyperparameter tuning, model stacking, and transfer learning) to maximize the accuracy of outcome prediction. Results: For prediction of neurological outcome, our model combining EHR and PTS features achieved a higher sensitivity (0.78), specificity (0.88), and AUC (0.87±0.01) compared to the APACHE baseline standard model (AUC: 0.74±0.01, sensitivity: 0.77, specificity: 0.63). Also, for prediction of mortality our model (AUC: 0.81±0.01, sensitivity: 0.78, specificity: 0.71) outperformed the APACHE clinical baseline (AUC: 0.75±0.01, sensitivity: 0.86, specificity: 0.56) by 7%. The integration of PTS with EHR data increased mean AUC by 4% for neurological outcome and 2% for mortality. Conclusion: Results demonstrate that for both neurological outcome and mortality prediction, our ensemble model was significantly more effective compared to the baseline APACHE model. Additionally, we find that PTS data adds to the discriminative power of clinical models. With appropriate validation in prospective cohorts, these findings could be used as point-of-care references to aid ICU physicians in clinical decision-making.

Falls represent a major public health risk worldwide for the elderly people. A fall not assisted in time can cause functional impairment in an elderly and a significant decrease in his mobility, independence, and life quality. In this sense, we propose IoTE-Fall system, an intelligent system for detecting falls of elderly people in indoor environments that takes advantages of the Internet of Thing and the ensemble machine learning algorithm. IoTE-Fall system employs a 3D-axis accelerometer embedded into a 6LowPAN wearable device capable of capturing in real time the data of the movements of elderly volunteers. To provide high efficiency in fall detection, in this paper, four machine learning algorithms (classifiers): decision trees, ensemble, logistic regression, and Deepnets are evaluated in terms of AUC ROC, training time and testing time. The acceleration readings are processed and analyzed at the edge of the network using an ensemble-based predictor model that is identified as the most suitable predictor for fall detection. The experiment results from collection data, interoperability services, data processing, data analysis, alert emergency service, and cloud services show that our system achieves accuracy, precision, sensitivity, and specificity above 94%.

A machine learning approach to solve a multiple regression problem is considered. Mass concentration of aerosol particles in the surface layer of the atmosphere was used as a dependent variable. The aerosol optical depth of the atmosphere and a number of meteorological parameters from the ECMWF ERA5 reanalysis database were chosen as predictors. The problem was solved using an ensemble machine learning algorithm - a random forest.

Warpage prediction of Injection-molded PVC part using ensemble machine learning algorithm

Laboratory-based hyperspectral imaging (HSI) is an optical non-destructive technology used to extract mineralogical information from bedrock drill cores. In the present study, drill core scanning in the long-wave infrared (LWIR; 8000–12,000 nm) wavelength region was used to map the dominant minerals in HSI pixels. Machine learning classification algorithms, including random forest (RF) and support vector machine, have previously been applied to the mineral characterization of drill core hyperspectral data. The objectives of this study are to expand semi-automated mineral mapping by investigating the mapping accuracy, generalization potential, and classification ability of cutting-edge methods, such as various ensemble machine learning algorithms and deep learning semantic segmentation. In the present study, the mapping of quartz, talc, chlorite, and mixtures thereof in HSI data was performed using the ENVINet5 algorithm, which is based on the U-net deep learning network and four decision tree ensemble algorithms, including RF, gradient-boosting decision tree (GBDT), light gradient-boosting machine (LightGBM), AdaBoost, and bagging. Prior to training the classification models, endmember selection was employed using the Sequential Maximum Angle Convex Cone endmember extraction method to prepare the samples used in the model training and evaluation of the classification results. The results show that the GBDT and LightGBM classifiers outperformed the other classification models with overall accuracies of 89.43% and 89.22%, respectively. The results of the other classifiers showed overall accuracies of 87.32%, 87.33%, 82.74%, and 78.32% for RF, bagging, ENVINet5, and AdaBoost, respectively. Therefore, the findings of this study confirm that the ensemble machine learning algorithms are efficient tools to analyze drill core HSI data and map dominant minerals. Moreover, the implementation of deep learning methods for mineral mapping from HSI drill core data should be further explored and adjusted.

Cheese-making traits in dairy cattle are important to the dairy industry but are difficult to measure at the individual level because there are limitations on collecting phenotypic information. Mid-infrared spectroscopy has its advantages, but it can only be used during monthly milk recordings. Recently, in-line devices for real-time analysis of milk quality have been developed. The AfiLab recording system (Afimilk) offers significant benefits as phenotypes can be collected from each cow at each milking session. The objective of this study was to assess the potential of integrating AfiLab real-time milk analyzer measures with the stacking ensemble learning technique using heterogeneous base learners for the in-line daily monitoring of cheese-making traits in Holstein cattle with a view to developing a precision livestock farming system for monitoring the technological quality of milk. Data and samples for wet-laboratory analyses were collected from 499 Holstein cows belonging to 2 farms where the AfiLab system was installed. The traits of concern were 9 milk coagulation traits [3 milk coagulation properties (MCP), and 6 curd firming traits (CFt)], and 7 cheese-making traits [3 cheese yield (CY) traits, and 4 milk nutrient recovery in the curd (REC) traits]. The near-infrared AfiLab spectral data and on-farm information (days in milk and parity) were used to assess the predictive ability of different statistical methods [elastic net (EN), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), and artificial neural network (ANN)] across different cross-validation scenarios. These statistical methods were considered the base learners, which were then combined in a stacking ensemble learning. Results indicate that including information on the cows (days in milk and parity) in the AfiLab infrared prediction increased its accuracy by 10.3% for traditional MCP, 13.8% for curd firming, 9.8% for CY, and 11.2% for REC traits compared with those obtained from near-infrared AfiLab alone. The statistical approaches exhibited high prediction accuracies (R2) averaged across the cross-validation scenarios for traditional MCP (0.58 for ANN, 0.55 for EN and GBM, 0.52 for XGBoost, and 0.62 for stacking ensemble), CFt (0.55 for ANN, 0.54 for EN and GBM, 0.53 for XGBoost, and 0.61 for stacking ensemble), and similar R2 averages for CY and REC (0.55 for ANN, 0.54 for EN and GBM, 0.53 for XGBoost, and 0.61 for stacking ensemble). The ANN approach was more accurate than the other base learners (EN, GBM, and XGBoost) and improved accuracy across cross-validation scenarios on average by 7% for traditional MCP, 5% for CFt, 8% for CY, and 7% for REC. The stacking ensemble method improved prediction accuracy by 3% to 31% for traditional MCP, 2% to 26% for CFt, 1% to 38% for CY traits, and 2% to 27% for REC traits compared with the base learners. The prediction accuracies of the different approaches evaluated tended to decrease from the 10-fold cross-validation to the independent validation scenario, although there was a smaller reduction in prediction accuracy with the stacking ensemble learning technique across all the cross-validation scenarios. Our results show that combining in-line on-farm information with stacking ensemble machine learning represents an effective alternative for obtaining robust daily predictions of milk cheese-making traits.

Robust multivariate time series forecasting is crucial in many cyberphysical and Internet of Things applications. Existing state-of-the-art robust forecasting models decompose time series into independent functions covering trends and periodicities. However, these independent functions fail to capture correlations among multiple time series, thereby reducing prediction accuracy. Moreover, existing robust forecasting models treat certain abrupt but normal changes, e.g., caused by holidays, as outliers because they occur infrequently and have data distributions that resemble those of outliers. This exacerbates model bias and reduces prediction accuracy. This paper aims to capture correlations across multiple time series and abrupt but normal changes, thereby improving prediction accuracy. We employ weak labels to partition the dataset into source and target domains. Then, we propose the Domain Adversarial Robust Forecaster (DARF). This forecasting model is based on adversarial domain adaptation and includes two novel modules: Correlated Robust Forecaster (CORF) and Domain Critic. Specifically, CORF constitutes an encoder-decoder framework proficient at robust multivariate time series forecasting, and Domain Critic works to reduce data bias. Extensive experiments and discussions show that DARF is capable of state-of-the-art forecasting accuracy.

Disastrous natural hazards, such as landslides, floods, and forest fires cause a serious threat to natural resources, assets and human lives. Consequently, landslide risk assessment has become requisite for managing the resources in future. This study was designed to develop four ensemble metaheuristic machine learning algorithms, such as grey wolf optimized based artificial neural network (GW-ANN), grey wolf optimized based random forest (GW-RF), particle swarm optimization optimized based ANN (PSO-ANN), and PSO optimized based RF for modeling rainfall-induced landslide susceptibility (LS) in Aqabat Al-Sulbat, Asir region, Saudi Arabia, which observes landslide frequently. To obtain very high precision and robust prediction from machine learning algorithms, the grey wolf and PSO optimization algorithms were integrated to develop new ensemble machine learning techniques. Subsequently, LS maps produced by training dataset were validated using the receiver operating characteristics (ROC) curve based on the testing dataset. Based on the area under curve (AUC) value of ROC curve, the best method for LS modeling was selected. We developed ROC curve-based sensitivity analysis to investigate the influence of the parameters for LS modeling. The Gumble extreme value distribution was employed to estimate the rainfall at 2, 5, 10, 20, 50, and 100 year return periods. Then, the landslide hazard maps were prepared at different return periods by integrating the best LS model and estimated rainfall at different return periods. The theory of danger pixels was employed to prepare a final risk assessment of the resources, which have been exposed to the landslide. The results showed that 27–42 and 6–15 km2 were predicted as the very high and high LS zones using four ensemble metaheuristic machine learning algorithms. Based on the area under curve (AUC) of ROC, GR-ANN (AUC-0.905) appeared as the best model for LS modeling. The areas under high and very high landslide hazard were gradually increased over the progression of time (26 km2 at the 2 year return period and 40 km2 at the 100 year return period for the high landslide hazard zone, and 6 km2 at the 2 year return period and 20 km2 at the 100 year return period for the very high landslide hazard zone). Similarly, the areas of danger pixel also increased gradually from the 2 to 100 year return periods (37 km2 to 62 km2). Various natural resources, such as scrubland, built up, and sparse vegetation, were identified under risk zone due to landslide hazards. In addition, these resources would be exposed extensively to landslides over the advancement of return periods. Therefore, the outcome of the present study will help planners and scientists to propose high precision management plans for protecting natural resources, which have been exposed to landslides.

This study looked at novel data sources for cardiovascular risk prediction including detailed lifestyle questionnaire and continuous blood pressure monitoring, using ensemble machine learning algorithms (MLAs). The reference conventional risk score compared against was the Framingham Risk Score (FRS). The outcome variables were low or high risk based on calcium score 0 or calcium score 100 and above. Ensemble MLAs were built based on naive bayes, random forest and support vector classifier for low risk and generalized linear regression, support vector regressor and stochastic gradient descent regressor for high risk categories. MLAs were trained on 600 Southeast Asians aged 21 to 69 years free of cardiovascular disease. All MLAs outperformed the FRS for low and high-risk categories. MLA based on lifestyle questionnaire only achieved AUC of 0.715 (95% CI 0.681, 0.750) and 0.710 (95% CI 0.653, 0.766) for low and high risk respectively. Combining all groups of risk factors (lifestyle survey questionnaires, clinical blood tests, 24-h ambulatory blood pressure and heart rate monitoring) along with feature selection, prediction of low and high CVD risk groups were further enhanced to 0.791 (95% CI 0.759, 0.822) and 0.790 (95% CI 0.745, 0.836). Besides conventional predictors, self-reported physical activity, average daily heart rate, awake blood pressure variability and percentage time in diastolic hypertension were important contributors to CVD risk classification.

Natural or artificial selection could shape genetic architecture, e.g., the relationship between minor allele frequency (MAF) and the effect sizes of causal variants (CVs). This study aimed to investigate the impact of the MAF-effect size relationship (as a selection signature, S) on genomic prediction and heritability estimation in livestock, using both simulated data (Holstein) and real datasets (Holstein and pigs). We evaluated the performance of two models: (1) selection-adjusted genomic best linear unbiased prediction (GBLUP-S), and (2) MAF-stratified selection-adjusted genomic best linear unbiased prediction (GBLUP-SMS). Simulation results demonstrated that for traits under strong negative selection (S < -1), both GBLUP-S and GBLUP-SMS outperformed classic GBLUP. The prediction accuracy of GBLUP-S improved by 0.011-0.031, while GBLUP-SMS achieved a gain of 0.005-0.025. Furthermore, GBLUP-SMS exhibited lower sensitivity to variations in S-values, whereas GBLUP-S heavily relied on accurate S specification. When the true S was matched, GBLUP-SMS generated more unbiased (or comparable) heritability estimates and higher prediction accuracy relative to GBLUP-S. Critically, mismatched S in GBLUP-S led to increased bias in heritability estimates and reduced prediction accuracy. Cross-validation with real phenotypic data from Holsteins and pigs demonstrated that implementing selection-adjust methods improved prediction accuracy by 0.015 for FP in Holsteins and 0.01 for T1 in pigs, while enhancing the unbiasedness of heritability estimates across all traits. Negative selection signatures were identified for cattle (S = -0.5) and pig T1, T2, and T3 (S = -1.5, -1, and -2, respectively). These findings advance the theoretical framework of GBLUP-based genomic prediction and heritability estimation.

The importance of an accurate branch prediction mechanism has been well documented. Since the introduction of gshare and the observation that aliasing in the PHT is a major factor in reducing prediction accuracy, several schemes have been proposed to reduce aliasing in the PHT. All these schemes are aimed at maximizing the prediction accuracy with the fewest resources. In this paper we introduce Yet Another Global Scheme (YAGS)-a new scheme to reduce the aliasing in the PHT-that combines the strong points of several previous schemes. YAGS introduces tags into the PHT that allows it to be reduced without sacrificing key branch outcome information. The size reduction more than offsets the cost of the tags. Our experimental results show that YAGS gives better prediction accuracy for the SPEC95 benchmark suite than several leading prediction schemes, for the same cost. It also performs better than the other schemes in the presence of a context switch. Finally, YAGS displays good results for the go benchmark, which is of special interest since it has a large number of static branches and reflects situations where aliasing in the PHT can be a problem.

The availability of data from electronic health records facilitates the development and evaluation of risk-prediction models, but estimation of prediction accuracy could be limited by outcome misclassification, which can arise if events are not captured. We evaluate the robustness of prediction accuracy summaries, obtained from receiver operating characteristic curves and risk-reclassification methods, if events are not captured (i.e., "false negatives"). We derive estimators for sensitivity and specificity if misclassification is independent of marker values. In simulation studies, we quantify the potential for bias in prediction accuracy summaries if misclassification depends on marker values. We compare the accuracy of alternative prognostic models for 30-day all-cause hospital readmission among 4548 patients discharged from the University of Pennsylvania Health System with a primary diagnosis of heart failure. Simulation studies indicate that if misclassification depends on marker values, then the estimated accuracy improvement is also biased, but the direction of the bias depends on the direction of the association between markers and the probability of misclassification. In our application, 29% of the 1143 readmitted patients were readmitted to a hospital elsewhere in Pennsylvania, which reduced prediction accuracy. Outcome misclassification can result in erroneous conclusions regarding the accuracy of risk-prediction models.

Existing preference prediction techniques can require that an entire preference structure be constructed for a user. These structures, such as Conditional Outcome Preference Networks (COP-nets), can grow exponentially in the number of attributes describing the outcomes. In this paper, a new approach for constructing COP-nets, using A* search, is introduced. Using this approach, partial COP-nets can be constructed on demand instead of generating the entire structure. Experimental results show that the new method yields enormous savings in time and memory requirements, with only a modest reduction in prediction accuracy.

Differential pulse code modulation (DPCM) algorithms are widely used to compress gray-scale pictures. A critical element in a DPCM algorithm is the accurate prediction of the pixel gray-levels in the input picture. The switched predictors used in modern DPCM algorithms are generally accurate when the input picture is free of noise. However, even small amounts of noise in the input picture will cause a substantial reduction in prediction accuracy and in turn a reduction in compression efficiency. In this paper we describe a novel fuzzy rule-based predictor for use in a lossless DPCM algorithm. For noisy pictures, the accuracy of the new predictor is consistently higher than the accuracy of standard switched predictors.