Maximize Emergency Data Output in WBAN by Using A Machine Learning Approach

Resumen

WBAN, or Wireless Body Area Network, has received a lot of interest due to its selfautomation
and improved technology. Many researchers have worked in this area. WBAN's
most challenging difficulty is dealing with diversified traffic on a network with limited
resources. Some sensed data are considered as more important than others in the healthcare
WBAN due to their critical nature. Such critical information must be provided within a
certain time range. Data transmission with loss and delay may not be tolerated in these
systems; hence, an intelligent algorithm to deal with these systems is necessary. As a
consequence, this technology might be employed in medical emergencies to quickly diagnose
and treat patients. Support Vector Machine (SVM) and Random Forest (RF) classifiers are
used to increase classification accuracy; they are Machine Learning Techniques. This method
is in charge of classifying each incoming packet and giving it a priority.