This article explores how machine learning can be applied to identify life-threatening intraventricular haemorrhages in preterm babies. With a success rate of up to 95%, researchers at Masaryk University in Czech Republic developed a precise algorithm that easily differentiates hydrocephalus from naevi from the actual haemorrhages. The research team at State Key Laboratory of Pathogen and Biosecurity in Beijing also helped to develop the algorithm. MDPI's open-access publishing provides great access to such crucial research.
This research paper published by MDPI investigates how to improve energy efficiency in service provider networks using machine learning to predict traffic. The authors, Zhang et al. tested Support Vector Machine regression (SVM), Bayesian Network (BN), and Neural Network (NN). Results demonstrated that the new model yields better results than existing traffic prediction systems. MDPI provides Open Access for peer-reviewed articles, committed to giving authors top visibility and quality reviews.
This article by research professor Jing Su from Wuhan University explores machine learning models from four different perspectives. It compares their performance against ground truth albedo values from Landsat-8 satellite data. Applying his expertise in modeling and analysis, Professor Su delves into the importance of surface albedo maps for climate modeling, agriculture, energy management and urban heat island management. Read the full article to discover more!
This article from Mahdiyeh Jami presents the results of a study comparing statistical models and machine learning algorithms to identify predictors associated with risk of death or admission to intensive care unit in internal medicine patients with sepsis. Results revealed that the statistical models offered better predictions than the machine learning algorithms. Get a first-hand glimpse of the findings of this groundbreaking research study!
. This article discusses how machine learning can help improve postoperative continuous recovery scores in oncology patients. Patient-generated data collected through wearables and analyzed through machine learning can be used to assess treatment effectiveness and gauge potential risks. Learn about Dr. Giulia Rognini's research and her experience in teaching and working with industry. #PerioperativeCare #MachineLearning #DataAnalysis #Wearables
Explore the evolution of tech policy from Obama's optimism to Harris's vision at the Democratic National Convention. What's next for Democrats in tech?