ANFIS and Deep Learning based missing sensor data prediction in IoT


GÜZEL M., Kok I., AKAY D., Ozdemir S.

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, vol.32, no.2, 2020 (Peer-Reviewed Journal) identifier identifier

  • Publication Type: Article / Article
  • Volume: 32 Issue: 2
  • Publication Date: 2020
  • Doi Number: 10.1002/cpe.5400
  • Journal Name: CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
  • Journal Indexes: Science Citation Index Expanded, Scopus, Aerospace Database, Applied Science & Technology Source, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Metadex, zbMATH, Civil Engineering Abstracts
  • Keywords: adaptive-network based fuzzy inference system(ANFIS), Deep Learning, Internet of Things (IoT), IoT data analysis, missing sensor data prediction, FUZZY C-MEANS, DATA IMPUTATION, INCOMPLETE DATA, INTERNET, MACHINE, THINGS, OPTIMIZATION

Abstract

Internet of Things (IoT) consists of billions of devices that generate big data which is characterized by the large volume, velocity, and heterogeneity. In the heterogeneous IoT ecosystem, it is not so surprising that these sensor-generated data are considered to be noisy, uncertain, erroneous, and missing due to the lack of battery power, communication errors, and malfunctioning devices. This paper presents Deep Learning (DL) and Adaptive-Network based Fuzzy Inference System (ANFIS) based prediction models for missing sensor data problem in IoT ecosystem. First, we build ANFIS based models and optimize their parameters. Then, we construct DL based models by using Long Short Term Memory (LSTM) network structure and optimize its parameters by applying the grid search method. Finally, we evaluate all the proposed models with Intel Berkeley Lab dataset. Experimental results demonstrate that the proposed models can significantly improve the prediction accuracy and may be promising for missing sensor data prediction.