Application of Interval Predictor Model Into Model Predictive Control

In this paper, interval prediction model is studied for model predictive control (MPC) strategy with unknown but bounded noise. After introducing the family of models and some basic information, some computational results are presented to construct interval predictor model, using linear regression structure whose regression parameters are included in a sphere parameter set. A size measure is used to scale the average amplitude of the predictor interval, then one optimal model that minimizes this size measure is efficiently computed by solving a linear programming problem. The active set approach is applied to solve the linear programming problem, and based on these optimization variables, the predictor interval of the considered model with sphere parameter set can be directly constructed. As for choosing a fixed non-negative number in our given size measure, a better choice is proposed by using the Karush-Kuhn-Tucker (KKT) optimality conditions. In order to apply interval prediction model into model predictive control, the midpoint of that interval is substituted in a quadratic optimization problem with inequality constrained condition to obtain the optimal control input. After formulating it as a standard quadratic optimization and deriving its dual form, the Gauss-Seidel algorithm is applied to solve the dual problem and convergence of Gauss-Seidel algorithm is provided too. Finally simulation examples confirm our theoretical results.

Multi-Gene Genetic Programming-Based Identification of a Dynamic Prediction Model of an Overhead Traveling Crane

This paper proposes a multi-gene genetic programming (MGGP) approach to identifying the dynamic prediction model for an overhead crane. The proposed method does not rely on expert knowledge of the system and therefore does not require a compromise between accuracy and complex, time-consuming modeling of nonlinear dynamics. MGGP is a multi-objective optimization problem, and both the mean square error (MSE) over the entire prediction horizon as well as the function complexity are minimized. In order to minimize the MSE an initial estimate of the gene weights is obtained by using the least squares approach, after which the Levenberg–Marquardt algorithm is used to find the local optimum for a k-step ahead predictor. The method was tested on both a simulation model obtained from the Euler–Lagrange equation with friction and the experimental stand. The simulation and the experimental stand were trained with varying control inputs, rope lengths and payload masses. The resulting predictor model was then validated on a testing set, and the results show the effectiveness of the proposed method.

Development of a model to predict recurrence after bronchial artery embolization for non-cancer related hemoptysis

Background Relapse after effective bronchial arterial embolization (BAE) for controlling hemoptysis is not uncommon. Studies reported diverse predictors of recurrence. However, a model to assess the probability of recurrence in non-cancer related hemoptysis patients after BAE has not been reported. This study was to develop a model to predict recurrence after BAE for non-cancer related hemoptysis. Methods The study cohort included 487 patients who underwent BAE for non-cancer-related hemoptysis between January 2015 and December 2019. We derived the model’s variables from univariate and multivariate Cox regression analyses. The model presented as a nomogram scaled by the proportional regression coefficient of each predictor. Model performance was assessed with respect to discrimination and calibration. Results One-month and 1-, 2-, 3- and 5-year recurrence-free rates were 94.5%, 88.0%, 81.4%, 76.2% and 73.8%, respectively. Risk factors for recurrence were underlying lung diseases and the presence of systemic arterial-pulmonary circulation shunts. This risk prediction model with two risk factors provided good discrimination (area under curve, 0.69; 95% confidence interval, 0.62–0.76), and lower prediction error (integrated Brier score, 0.143). Conclusion The proposed model based on routinely available clinical and imaging features demonstrates good performance for predicting recurrence of non-cancer-related hemoptysis after BAE. The model may assist clinicians in identifying higher-risk patients to improve the long-term efficacy of BAE.

Primer on binary logistic regression

Family medicine has traditionally prioritised patient care over research. However, recent recommendations to strengthen family medicine include calls to focus more on research including improving research methods used in the field. Binary logistic regression is one method frequently used in family medicine research to classify, explain or predict the values of some characteristic, behaviour or outcome. The binary logistic regression model relies on assumptions including independent observations, no perfect multicollinearity and linearity. The model produces ORs, which suggest increased, decreased or no change in odds of being in one category of the outcome with an increase in the value of the predictor. Model significance quantifies whether the model is better than the baseline value (ie, the percentage of people with the outcome) at explaining or predicting whether the observed cases in the data set have the outcome. One model fit measure is the count- R2, which is the percentage of observations where the model correctly predicted the outcome variable value. Related to the count- R2 are model sensitivity—the percentage of those with the outcome who were correctly predicted to have the outcome—and specificity—the percentage of those without the outcome who were correctly predicted to not have the outcome. Complete model reporting for binary logistic regression includes descriptive statistics, a statement on whether assumptions were checked and met, ORs and CIs for each predictor, overall model significance and overall model fit.

A new approach for location-specific seasonal outlooks of typhoon and super typhoon frequency across the Western North Pacific region

With an average of 26 tropical cyclones (TCs) per year, the western North Pacific (WNP) is the most active TC basin in the world. Considerable exposure lies in the coastal regions of the WNP, which extends from Japan in the north to the Philippines in the south, amplifying TC related impacts, including loss of life and damage to property, infrastructure and environment. This study presents a new location-specific typhoon (TY) and super typhoon (STY) outlook for the WNP basin and subregions, including China, Hong Kong, Japan, Korea, Philippines, Thailand, and Vietnam. Using multivariate Poisson regression and considering up to nine modes of ocean-atmospheric variability and teleconnection patterns that influence WNP TC behaviour, thousands of possible predictor model combinations are compared using an automated variable selection procedure. For each location, skillful TY and STY outlooks are generated up to 6 months before the start of the typhoon season, with rolling monthly updates enabling refinement of predicted TY and STY frequency. This unparalleled lead time allows end-users to make more informed decisions before and during the typhoon season.

Development and validation of a ferroptosis-related model for three digestive tract tumors based on a pan-cancer analysis

Aims: To develop a ferroptosis gene-based survival-predictor model for predicting the prognosis of patients with digestive tract tumors, a pan-caner analysis was performed. Materials & methods: Based on unsupervised clustering and the expression levels of ferroptosis genes, patients with cancer were divided into two clusters. The least absolute shrinkage and selection operator method Cox regression analysis was used to establish the survival-predictor model. Results: Based on the pan-cancer analysis, a 20 gene-based survival-predictor model for predicting survival rates was developed, which was validated in patients with hepatocellular carcinoma. Conclusion: The survival-predictor model accurately predicted the prognosis of patients with digestive tract tumors.

A strontium isoscape of Italy for provenance studies

We present a novel database of environmental and geological 87Sr/86Sr values (n = 1920) from Italy, using literature data and newly analysed samples, for provenance purposes. We collected both bioavailable and non-bioavailable (i.e. rocks and bulk soils) data to attain a broader view of the Sr isotope variability of the Italian peninsula. These data were used to build isotope variability maps, namely isoscapes, through Kriging interpolations. We employed two different Kriging models, namely Ordinary Kriging and Universal Kriging, with a geolithological map of Italy categorized in isotope classes as external predictor. Model performances were evaluated through a 10-fold cross validation, yielding accurate 87Sr/86Sr predictions with root mean squared errors (RMSE) ranging between 0.0020 and 0.0024, dependent on the Kriging model and the sample class. Overall, the produced maps highlight a heterogeneous distribution of the 87Sr/86Sr across Italy, with the highest radiogenic values (>0.71) mainly localized in three areas, namely the Alps (Northern Italy), the Tuscany/Latium (Central Italy) and Calabria/Sicily (Southern Italy) magmatic/metamorphic terrains. The rest of the peninsula is characterized by values ranging between 0.707 and 0.710, mostly linked to sedimentary geological units of mixed nature. Finally, we took advantage of the case study of Fratta Polesine, to underscore the importance of choosing appropriate samples when building the local isoscape and of exploring different end-members when interpreting the local Sr isotope variability in mobility and provenance studies. Our user-friendly maps and database are freely accessible through the Geonode platform and will be updated over time to offer a state-of-the-art reference in mobility and provenance studies across the Italian landscape.

Analisis Akurasi Model-Model Prediksi Financial Distress

This study aims to find the most accurate predictor model of financial distress. The company has the potential to go bankrupt. Bankruptcy can be predicted using an accurate predictor model as an early warning to anticipate financial distress. This research was conducted on the global retail industry which is included in Kantar's 2019 Top 30 Global Retails (EUR). The data in this study were taken from 60 annual reports for the 2018-2019 period and a sample of 30 on global retail companies. The accuracy rate is calculated by the number of correct predictions divided by the total data and multiplied by one hundred percent. This study compares four predictor models of financial distress, namely the Altman model, the Springate model, the Taffler model, and the Grover model. With the results of the study, the Grover model has the highest level of accuracy, which is 76.67%.

Prediction of COVID-19 deterioration in high-risk patients at diagnosis: an early warning score for advanced COVID-19 developed by machine learning

Purpose While more advanced COVID-19 necessitates medical interventions and hospitalization, patients with mild COVID-19 do not require this. Identifying patients at risk of progressing to advanced COVID-19 might guide treatment decisions, particularly for better prioritizing patients in need for hospitalization. Methods We developed a machine learning-based predictor for deriving a clinical score identifying patients with asymptomatic/mild COVID-19 at risk of progressing to advanced COVID-19. Clinical data from SARS-CoV-2 positive patients from the multicenter Lean European Open Survey on SARS-CoV-2 Infected Patients (LEOSS) were used for discovery (2020-03-16 to 2020-07-14) and validation (data from 2020-07-15 to 2021-02-16). Results The LEOSS dataset contains 473 baseline patient parameters measured at the first patient contact. After training the predictor model on a training dataset comprising 1233 patients, 20 of the 473 parameters were selected for the predictor model. From the predictor model, we delineated a composite predictive score (SACOV-19, Score for the prediction of an Advanced stage of COVID-19) with eleven variables. In the validation cohort (n = 2264 patients), we observed good prediction performance with an area under the curve (AUC) of 0.73 ± 0.01. Besides temperature, age, body mass index and smoking habit, variables indicating pulmonary involvement (respiration rate, oxygen saturation, dyspnea), inflammation (CRP, LDH, lymphocyte counts), and acute kidney injury at diagnosis were identified. For better interpretability, the predictor was translated into a web interface. Conclusion We present a machine learning-based predictor model and a clinical score for identifying patients at risk of developing advanced COVID-19.