Internet of Things data uncertainty measurement, prediction and outlier-removing method based on Gaussian process

Abstract

The invention relates to an Internet of Things data uncertainty measurement, prediction and outlier-removing method based on the Gaussian process. The method is a dynamical system method of estimating and collecting the standard deviation of Internet of Things perception sensor measurement errors and combining the Gaussian process modeling theory with autoregression model representations; prediction values and uncertainty measurement of observation data effective time sequence data are given, whether the data are missing values or outlier data is judged according to the information, and data supplement is correspondingly carried out. The method is a non-parameterized probability prediction method. Due to the fact that training set learning has the feature of tracing system dynamic states, judgment, early-warning and data supplement can be carried out on data exception and data missing phenomena in time according to the prediction value uncertainty and the sensor calibration standard deviation, the prediction error is small, and the accuracy is high. The Internet of Things data uncertainty measurement, prediction and outlier-removing method is used for controlling the quality of Internet of Things automatic observation data, and can ensure accuracy of collected data.

Description

technical field [0001] The invention belongs to the field of Internet of Things data processing, and in particular relates to a Gaussian process-based method for measuring, predicting and removing outliers of Internet of Things data, which is used for quality control of Internet of Things automatic observation data. technical background [0002] The agricultural production cycle is long and the influencing factors are complex. It is very difficult to understand the causal relationship. The potential of promoting agricultural production and development through big data technology has already emerged. With the rapid development of precision agriculture, smart agriculture, Internet of Things and cloud computing, agricultural data has also shown explosive growth. The Internet of Things has become one of the most important data collection tools for agricultural big data. [0003] Various sensors are widely used in modern agriculture to realize all-weather, multi-scale real-time ...

AI Technical Summary

Problems solved by technology

ARMA is simple to implement, but has the disadvantages of low prediction accuracy of low-order models and difficulty in determining parameters of high-order models; while neural network methods have defects such as slow convergence speed, difficult selection of hidden layer nodes, and large training data; Kalman filtering real-time Good performance, but there are problems such as low prediction accuracy for complex nonlinear systems

Therefore, the accuracy of the traditional time series data forecasting method is not high, and the above methods lack the uncertainty measurement of the forecast results

Images