Network technologies have facilitated the implementation of health services based on ubiquitous systems, allowing pervasive monitoring of patients in their daily activities without significantly interfering in their lifestyle. This event entails the need to ensure adequate management and security of healthcare environment networks. However, traffic monitoring became an arduous work, requiring autonomic mechanisms to describe the network's normal behavior. Thus, Digital Signature of Network Segment using Flow analysis (DSNSF) as a mechanism to assist the networks management through traffic characterization is introduced. For this purpose, three methods belonging to different groups of algorithms are used: the statistical procedure Principal Component Analysis (PCA), the Ant Colony Optimization (ACO) metaheuristic and Holt–Winters forecasting method. These methods characterize the traffic into two distinct levels. The first one is the network infrastructure, which encompasses the entire network, including non-healthcare data from different sectors which compose an e-health environment. Profile creation about traffic used for monitoring of patients' vital and behavioral signs identifies the second level. Also, an approach for anomaly detection is proposed, which is able to recognize unusual events that may affect the proper operation of the services provided by the network.