A Survey on Enhanced Big Sensor Error Detection Model Using K - Means Clustering Algorithm

Big Data concern large-volume, complex, growing data set with multiple, autonomous sources. With fast development of networking, data storage and data collection capacity Big Data are now rapidly expanding in all science and engineering domains including physical, biomedical sciences and biological. Wireless Sensor Networks (WSNs) have become a new monitoring solution for a variety of applications and information collections. Error occurring to sensor nodes are common due to the harsh environment where the sensor nodes are deployed and sensor device itself. To ensure the network quality of service it is important for the WSN to be able to detect the errors and take actions to keep away from further degradation of the service. However, these techniques do not give ef�cient support on quick detection and locating of errors in big sensor data sets. In this paper, develop a new data error detection approach which abuses the full computation capability of cloud platform and the network feature of WSN. That Proposed approach can significantly reduce the time for error detection and location in big data sets created by large scale sensor network systems with acceptable error detecting accuracy. In this paper explores using the K-Mean Clustering algorithm to further improve the accuracy of determining the number of error detection and attackers. In addition, it develops an integrated detection and localization system that can localize the positions of multiple error detection algorithms.