The missing of the sensing data is inevitable due to the inherent characteristic of Wireless Sensor Network (WSN),which affects various applications significantly. To solve the problem, an estimation algorithm for missing values based on attribute correlation of the sensing data was proposed. The multiple regression model was adopted to estimate missing values of attribute-correlated sensing data. Meanwhile, a data interleaved transmitting strategy was proposed to improve the robustness of the algorithm. The simulation results show that the proposed algorithm can estimate the missing values and is more accurate and reliable than some algorithms based on temporal and spatial correlation such as Linear interpolation Model (LM) algorithm and the traditional Nearest Neighbor Interpolation (NNI) algorithm.

Since the data gathered in Wireless Sensor Network (WSN) are inaccurate and unreliable, a flexible space model based on the spatial correlation of sensor data was defined, and an adaptive neighbor-space approach for data cleansing (ANSA) was proposed. The approach adjusted neighbor-space dynamically according to sensor data fluctuation and calculated the weighted average of neighbors' measurements to clean local raw data. The experimental results show that, the sensor data error after cleansing by the proposed approach is less than 0.5, and compared to the classic Weighted Moving Average (WMA), it is more accurate and the energy consumption is reduced by about 36%.