Convolutional and Recurrent Neural Networks for Activity Recognition in Smart Environment

Abstract : Convolutional Neural Networks (CNN) are very useful for fully automatic extraction of discriminative features from raw sensor data. This is an important problem in activity recognition, which is of enormous interest in ambient sensor environments due to its universality on various applications. Activity recognition in smart homes uses large amounts of time-series sensor data to infer daily living activities and to extract effective features from those activities, which is a challenging task. In this paper we demonstrate the use of the CNN and a comparison of results, which has been performed with Long Short Term Memory (LSTM), recurrent neural networks and other machine learning algorithms, including Naive Bayes, Hidden Markov Models, Hidden Semi-Markov Models and Conditional Random Fields. The experimental results on publicly available smart home datasets demonstrate that the performance of 1D-CNN is similar to LSTM and better than the other probabilistic models.
Document type :
Book sections
Complete list of metadatas
Contributor : Matthieu Geist <>
Submitted on : Monday, November 6, 2017 - 5:07:42 PM
Last modification on : Thursday, April 5, 2018 - 12:30:25 PM


  • HAL Id : hal-01629732, version 1


Deepika Singh, Erinc Merdivan, Sten Hanke, Johannes Kropf, Matthieu Geist, et al.. Convolutional and Recurrent Neural Networks for Activity Recognition in Smart Environment. A. Holzinger; R. Goebel; M. Ferri; V. Palade. Towards Integrative Machine Learning and Knowledge Extraction , 10344, springer, pp.194-205, 2017, Lecture Notes in Computer Science. ⟨hal-01629732⟩



Record views