Human activity vibrations

Sakdirat Kaewunruen, Jessada Sresakoolchai, Junhui Huang, Satoru Harada, Wisinee Wisetjindawat

Research output: Contribution to journalArticlepeer-review

18 Downloads (Pure)

Abstract

We present a unique, comprehensive dataset that provides the pattern of five activities walking, cycling, taking a train, a bus, or a taxi. The measurements are carried out by embedded sensor accelerometers in smartphones. The dataset offers dynamic responses of subjects carrying smartphones in varied styles as they perform the five activities through vibrations acquired by accelerometers. The dataset contains corresponding time stamps and vibrations in three directions longitudinal, horizontal, and vertically stored in an Excel Macro-enabled Workbook (xlsm) format that can be used to train an AI model in a smartphone which has the potential to collect people’s vibration data and decide what movement is being conducted. Moreover, with more data received, the database can be updated and used to train the model with a larger dataset. The prevalence of the smartphone opens the door to crowdsensing, which leads to the pattern of people taking public transport being understood. Furthermore, the time consumed in each activity is available in the dataset. Therefore, with a better understanding of people using public transport, services and schedules can be planned perceptively.
Original languageEnglish
Article number104
Number of pages9
JournalData
Volume6
Issue number10
DOIs
Publication statusPublished - 30 Sep 2021

Keywords

  • human activity
  • smartphone
  • accelerometer

Fingerprint

Dive into the research topics of 'Human activity vibrations'. Together they form a unique fingerprint.

Cite this