Ali M. Aseere^1,*, Ayodele Lasisi²

Intelligent Automation & Soft Computing, Vol.27, No.3, pp. 683-699, 2021, DOI:10.32604/iasc.2021.014811 - 01 March 2021

Abstract In the absence of fast and adequate measures to combat them, life-threatening diseases are catastrophic to human health. Computational intelligent algorithms characterized by their adaptability, robustness, diversity, and recognition abilities allow for the diagnosis of medical diseases. This enhances the decision-making process of physicians. The objective is to predict and classify diseases accurately. In this paper, we proposed a multi-agent stacked ensemble classifier based on a vaguely quantified rough set, simple logistic algorithm, sequential minimal optimization (SMO), and JRip. The vaguely quantified rough set (VQRS) is used for feature selection and eradicating noise in the More >

Bingjie Yan¹, Jun Wang¹, Zhen Zhang², Xiangyan Tang^{1, *}, Yize Zhou¹, Guopeng Zheng¹, Qi Zou¹, Yao Lu¹, Boyi Liu³, Wenxuan Tu⁴, Neal Xiong⁵

CMC-Computers, Materials & Continua, Vol.64, No.3, pp. 1473-1490, 2020, DOI:10.32604/cmc.2020.011317 - 30 June 2020

Abstract New coronavirus disease (COVID-19) has constituted a global pandemic and has spread to most countries and regions in the world. Through understanding the development trend of confirmed cases in a region, the government can control the pandemic by using the corresponding policies. However, the common traditional mathematical differential equations and population prediction models have limitations for time series population prediction, and even have large estimation errors. To address this issue, we propose an improved method for predicting confirmed cases based on LSTM (Long-Short Term Memory) neural network. This work compares the deviation between the experimental… More >

Daniel A. Pérez-Fentes¹, Francisco Gude², Miguel Blanco¹, Rosa Novoa¹, Camilo García Freire¹

Canadian Journal of Urology, Vol.20, No.6, pp. 7050-7059, 2013

Abstract Introduction: The aim of this study is to identify surgical, patient- and stone-related factors predictive of clinical success and complications after percutaneous nephrolithotomy (PCNL).
Materials and methods: We prospectively studied 100 consecutive PCNL procedures. Univariate and multiple regression models were used in order to identify which variables could act as independent predictors of PCNL outcomes. Success was defined as complete absence of fragments in a non-contrast CT. The Clavien-modified grading system was used to classify the complications.
Results: Univariate analysis showed that patients rendered stone-free had a significantly lower stone burden, shorter operating times, single stones and non-struvite… More >