Cardiac, diabetic and normal subjects classification using decision tree and result confirmation through orthostatic stress index

A Systematic Review on Prediction Techniques for Cardiac Disease

Mortality rate can be lowered with early prediction of cardiac diseases, which is one of the major issue in healthcare industry. In comparison of traditional methods, intelligent systems have potential to predict these diseases accurately at early stage even with complex data. Various intelligent DSS are presented by researchers for predicting this disease. To study the trends of these intelligent systems, to find the effective techniques for predicting cardiac disease and to find the future directions are the objective of this study. Therefore this paper presents a systematic review on state-of-art techniques based on ML, NN and FL. For analysis, we follow PRISMA statement and considered the studies presented from 2010 to 2020 from different databases. Analysis concluded that ML based techniques are broadly used for feature selection and classification and have the potential for the prediction of cardiac diseases. The future directions are to evaluate the rarely used prediction techniques and finding the way of improving them for model generalization with better prediction accuracy.

Machine learning-based prediction of phases in high-entropy alloys: A data article

A systematic framework for choosing the most determinant combination of predictor features and solving the multiclass phase classification problem associated with high-entropy alloy (HEA) was recently proposed [1]. The data associated with that research paper, titled "Machine learning-based prediction of phases in high-entropy alloys", is presented in this data article. This dataset is a systematic documentation and comprehensive survey of experimentally reported HEA microstructures. It contains microstructural phase experimental observations and metallurgy-specific features as introduced and reported in peer-reviewed research articles. The dataset is provided with this article as a supplementary file. Since the dataset was collected from experimental peer-reviewed articles, these data can provide insights into the microstructural characteristics of HEAs, can be used to improve the optimization HEA phases, and have an important role in machine learning, material informatics, as well as in other fields.

Human and Human-Interfaced AI Interactions: Modulation of Human Male Autonomic Nervous System via Pupil Mimicry

Pupillary alterations in virtual humans induce neurophysiological responses within an observer. Technological advances have enabled rapid developments in artificial intelligence (AI), from verbal systems, to visual AI interfaces with the ability to express, and respond to emotional states of a user. Visual AI interfaces are able to change their physical parameters, such as pupil diameter. Pupillary changes can alter heart rate, however, effects on heart rate variability (HRV) are unknown. HRV, is an autonomic, non-conscious parameter which monitors sympathetic and parasympathetic nervous system (PNS) activity. N = 34 male participants aged between 19–33 were subjected to a number of conditions such as pupil dilation, constriction and blushing. The present research is the first to investigate the effects of virtual human interactions on human HRV. Outcomes of this study were obtained using eye tracking and HRV measurements. Pupil dilation relative to constriction presented in the female virtual partner induced a significant right pupillary diameter increase (p = 0.041) in human observers. Additionally, female virtual partner pupil constriction relative to dilation induced a significant increase in participants’ PNS HRV response (p = 0.036). These findings indicate the ability of a female virtual interaction partner to modulate parasympathetic autonomic functioning in young healthy male humans. This allows first insights into the effects of interacting with virtual AI interaction partners, on human autonomic functioning, and may aid development of future virtual humans, and their implementation into relevant clinical settings.