A Novel Input Set for LSTM-based Transport Mode Detection


Asci G., GÜVENSAN M. A.

IEEE International Conference on Pervasive Computing and Communications (PerCom), Kyoto, Japan, 11 - 15 March 2019, pp.107-112 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/percomw.2019.8730799
  • City: Kyoto
  • Country: Japan
  • Page Numbers: pp.107-112
  • Keywords: Transport Mode Detection, Recurrent Neural Network, Time-Domain and Frequency Domain Features, DESIGN
  • Yıldız Technical University Affiliated: Yes

Abstract

The capability of mobile phones are increasing with the development of hardware and software technology. Especially sensors on smartphones enable to collect environmental and personal information. Thus, with the help of smartphones, human activity recognition and transport mode detection (TMD) become the main research areas in the last decade. This study aims to introduce a novel input set for daily activities mainly for transportation modes in order to increase the detection rate. In this study, the frame-based novel input set consisting of time-domain and frequency-domain features is fed to LSTM network. Thus, the classification ratio on HTC public dataset for 10 different transportation modes is climbed up to 97% which is 2% more than the state-of-the-art method in the literature.