Multi-Dimensional Joint Prediction Model for IoT Sensor Data Search

Wenhao Fan,Haosong Liu,Jielong Tang,Cong Zhang,Fan Wu,Yuanan Liu

doi:10.1109/access.2019.2927239

Wenhao Fan, Haosong Liu + Show 4 more

Open Access

https://doi.org/10.1109/access.2019.2927239

Copy DOI

Abstract

In recent years, with the rapid deployment of various Internet of Things (IoT) devices, it becomes a crucial and practical challenge to enable real-time search for objects, data, and services in the Internet of Everything. The IoT data prediction model can not only provide solutions for the real-time acquisition of the IoT sensor data but also provide more meaningful applications than the traditional IoT event detection model. In this paper, we use the complex time series formed by various types of sensors to establish a multi-dimensional feature selection model and a dynamic sensor-data prediction model. Compared with the traditional data prediction model, our model improves the accuracy and stability of the long-term prediction results of the IoT sensor data. Finally, we evaluate our prediction model using the Intel Berkeley Research Lab sensor data with an accuracy of over 98% and 92% accuracy on the Chicago Park District weather&water data.

Highlights

With the gradual deepening of the Internet of Things(IoT) applications and the improvement of people’s life requirements, people’s demand for real-time and reliable access to physical world entity information is growing
According to the characteristics of the IoT, this paper proposes a sensor correlation feature selection algorithm to dynamically predict the future values of the sensors
In this paper, we propose an adaptive feature selection algorithm and a multi-dimensional sensor data prediction model for dynamic IoT data which can improve the accuracy of sensor time series long-period prediction

Summary

SPECIAL SECTION ON DATA MINING FOR INTERNET OF THINGS

Received June 1, 2019, accepted June 22, 2019, date of publication July 8, 2019, date of current version July 25, 2019. CONG ZHANG 1, (Student Member, IEEE), YUANAN LIU1, FAN WU 1, (Member, IEEE), WENHAO FAN 1, (Member, IEEE), JIELONG TANG2, AND HAOSONG LIU2

INTRODUCTION

Findings

CONCLUSION