ABSTRACT

Monitoring human activities using wearable wireless sensor nodes has the potential to enable many useful applications for everyday situations. The long-term lifestyle categorization can greatly improve healthcare by gathering information about quality of life; aiding the diagnosis and tracking of certain diseases. The deployment of an automatic and computationally-efficient algorithm reduces the complexities involved in the detection and recognition of human activities in a distributed on Body sensor network server. Directory service is a useful aid human looking for information on Network Data. A directory services is a pre-categorized list of topics containing many links for each topic. However, most directory services are maintained manually now and face many drawbacks. Therefore the task of automatic categorization of new data into the topics of directory services becomes very necessary. BSN data categorization is more difficult due to a large variation of noisy information embedded in Sensor network data. This paper suggests a new Centroid based approach for Categorization for BSN data. We further introduce a new algorithm through centroid based approach for extraction of BSN data categorization and show that it achieves about more improvement over other BSN data categorization methods. Experimental results show that our proposed Centroid-based BSN data categorization algorithm achieves an approximately 13.8% improvement for BSN data categorization algorithm.