Coronavirus disease 2019 (COVID-19): survival analysis using deep learning and Cox regression model

Pattern Analysis and Applications - Coronavirus (COVID-19) is one of the most serious problems that has caused stopping the wheel of life all over the world. It is widely spread to the extent that...     

Bayesian belief-based model for reliability improvement of the digital reactor protection system

Nuclear Science and Techniques - This paper introduces some latest developments regarding the X-ray imaging methodology and applications of the X-ray imaging and biomedical application beamline...     

On-line self-tuning control of processes with inaccessible state

The practical implementation of an explicit multivariable state-space self-tuning controller using a hybrid configured microcomputer system is described. The control structure is based on the minimization of a multistage quadratic performance index using dynamic programming or a single-stage performance index based on a Lyapunov function. Measurement of readily available output measurements from the controlled plant is all that is required. The system hardware is centered around a 16-b Sirius microcomputer interfaced to an analog computer on which the plant is simulated. Application software is handled under the MS-DOS operating system using a mixture of high-level and low-level programming languages     

Handling missing and outliers values by enhanced algorithms for an accurate diabetic classification system

Recently, healthcare data analysis has become an attractive research topic. Data gathering is the first step in data analysis and processing. During the collection of the data, some errors may occur due to human mistakes, devices’ errors, or the transmission process noise. The correct treatment of the missed data and outliers conserve the data size and improve the model’s performance. This paper provides two enhanced algorithms to handle missing values and outliers in big datasets. The main idea is dividing the dataset into its different classes, or clustering it by using k-means++, then calculate the average value of each part, finally replace the missed data and outliers with its corresponding part mean value. The projected imputation and outliers’ data handling algorithms are tested on a dataset called Pima Indian diabetic, which contains 2768 patients dividing into 952 diabetic and 1816 controls. Four classifiers (Random Forest, Decision Tree, Support Vector Machine, and Naïve Bayes) are used to evaluate the effect of the proposed algorithms. The results show that the proposed algorithms improve classification accuracy by 8% and decrease the RMSE by 17% over Deep Learning (DL). DL is the most powerful algorithms used in repairing the missed data.

     

Correction to: Handling missing and outliers values by enhanced algorithms for an accurate diabetic classification system

Multimedia Tools and Applications - A Correction to this paper has been published: https://doi.org/10.1007/s11042-021-10843-x