Machine Learning: An Algorithmic Perspective
Machine Learning: An Algorithmic Perspective
MuZi: Multi-channel ZigBee Networks for Avoiding WiFi Interference
ITHINGSCPSCOM '11 Proceedings of the 2011 International Conference on Internet of Things and 4th International Conference on Cyber, Physical and Social Computing
On the mechanisms and effects of calibrating RSSI measurements for 802.15.4 radios
EWSN'10 Proceedings of the 7th European conference on Wireless Sensor Networks
ISMS '12 Proceedings of the 2012 Third International Conference on Intelligent Systems Modelling and Simulation
Hi-index | 0.00 |
Coexistence problem occurs when a single WBAN(Wireless Body Area Network) locates in multiple WBANs environment. In that case, WBANs are suffered from serious channel interferences which may degrade the performance of each WBAN due to failure of data transmission. Because WBAN handles physical signal or emergency data affecting human life, WBAN requires the detection of coexistence condition to guarantee reliable communication continuously for each sensor node of WBAN. In this paper, we present a prediction algorithm to detect coexistence problem efficiently in multiple WBANs environment. The algorithm measures PRR(Packet Reception Ratio) and SINR(Signal to Interference and Noise Ratio) to detect interference reliably. In order to handle coexistence problem efficiently, the algorithm employs the naive Bayesian classifier which is one of machine learning techniques to classify the coexistence condition into four states. We conduct extensive simulations for coexistence detection with various packet transmit rates of sender node and speeds of mobile WBAN by using Castalia 3.2 simulator based on OMNet++ platform. Consequently, we demonstrate that the proposed algorithm provides more reliable and accurate performance than existing studies to detect coexistence in multiple WBANs environment.