A Comparative Study of Speculative Retrieval for Multi-Modal Data Trails: Towards User-Friendly Human-Vehicle Interactions

Yaohua Wang, Zhengtao Huang, Rongze Li, Xinyu Yin, Min Luo, Zheng Zhang, Xu Sun

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

In the era of growing developments in Autonomous Vehicles, the importance of Human-Vehicle Interaction has become apparent. However, the requirements of retrieving in-vehicle drivers' multi-modal data trails, by utilizing embedded sensors, have been consid-ered user unfriendly and impractical. Hence, speculative designs, for in-vehicle multi-modal data retrieval, has been demanded for future personalized and intelligent Human-Vehicle Interaction. In this paper, we explore the feasibility to utilize facial recog-nition techniques to build in-vehicle multi-modal data retrieval. We first perform a comprehensive user study to collect relevant data and extra trails through sensors, cameras and questionnaire. Then, we build the whole pipeline through Convolution Neural Net-works to predict multi-model values of three particular categories of data, which are Heart Rate, Skin Conductance and Vehicle Speed, by solely taking facial expressions as input. We further evaluate and validate its effectiveness within the data set, which suggest the promising future of Speculative Designs for Multi-modal Data Retrieval through this approach.

Original languageEnglish
Title of host publicationICCAI 2020 - Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence
PublisherAssociation for Computing Machinery
Pages99-103
Number of pages5
ISBN (Electronic)9781450377089
DOIs
Publication statusPublished - 23 Apr 2020
Event6th International Conference on Computing and Artificial Intelligence, ICCAI 2020 - Virtual, Online, China
Duration: 23 Apr 202026 Apr 2020

Publication series

NameACM International Conference Proceeding Series

Conference

Conference6th International Conference on Computing and Artificial Intelligence, ICCAI 2020
Country/TerritoryChina
CityVirtual, Online
Period23/04/2026/04/20

Keywords

  • Human-Vehicle interaction
  • facial recognition
  • multi-modal data streams

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'A Comparative Study of Speculative Retrieval for Multi-Modal Data Trails: Towards User-Friendly Human-Vehicle Interactions'. Together they form a unique fingerprint.

Cite this