Michigan State University
When virtual reality meets IoT in the gym : enabling immersive and interactive machine exercise
Abstract
dc:description"The advent of head mounted displays (HMDs) such as Oculus Rift, Samsung Gear VR, and Microsoft HoloLens are turning immersive virtual reality (VR) into reality. As one of its most compelling applications, we envision that VR will revolutionize the personal fitness experience in our daily lives. Towards this vision, we present JARVIS, a novel immersive exercise tracking applications enabled by miniature IoT sensing devices combined with a mobile HMD device. By attaching IoT sensing devices on any gym machines, JARVIS continuously tracks exercise progress and assesses exercise quality in real-time, enabling effective interaction with machines. By converting the captured exercise progress and quality information to VR inputs, it creates an immersive exercise experience with a virtual avatar to guide machine exercises. We have conducted extensive experiments to validate the performance of JARVIS. It achieves 97.96% of repetition segmentation accuracy without knowing the current exercise type, as well as 99.08% of exercise type recognition accuracy in 1.22 repetitions on average. We have also conducted a real-world deployment study to examine the efficacy of the proposed platform. By analyzing muscle activities using high-fidelity clinical surface Electromyography (sEMG) sensors, our results indicate that our VR/IoT-based platform could provide an engaging and effective guidance to exercisers for their strength training."--Page ii.
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Rabbi, Md. Fazlay
- Contributors dc:contributor
-
- Zhang, Mi
- Park, Taiwoo
- Morris, Daniel
Subjects
dc:subject × 3Rights
dc:rights- Statement dc:rights
-
- In Copyright
- Language dc:language
- English
Identifiers
dc:identifier.*- Identifier
-
etd:4529
isbn:9781369429237
isbn:1369429231
oclc:993441217
umi:10245280
local:Rabbi_grad.msu_0128N_14962 - OAI record oai:identifier
- https://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_4529