Works (2)
Updated: June 15th, 2023 07:07
2017 article
Energy-efficient activity recognition via multiple time-scale analysis
Lokare, N., Samadi, S., Zhong, B., Gonzalez, L., Mohammadzadeh, F., & Lobaton, E. (2017, November 1). 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1466–1472.
topics (OpenAlex): Context-Aware Activity Recognition Systems; Non-Invasive Vital Sign Monitoring; IoT and Edge/Fog Computing
TL;DR:
This work proposes a novel power-efficient strategy for supervised human activity recognition using a multiple time-scale approach, which takes into account various window sizes, and shows that the proposed approach Sequential Maximum-Likelihood achieves high F1 score across all activities while providing lower power consumption than the standard Maximum- likelihood approach.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
7. Affordable and Clean Energy
(OpenAlex)
Sources: NC State University Libraries, NC State University Libraries, ORCID
Added: August 6, 2018
2016 article
Comparing wearable devices with wet and textile electrodes for activity recognition
Lokare, N., Gonzalez, L., & Lobaton, E. (2016, August 1). 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3539–3542.
MeSH headings : Artifacts; Electrocardiography / instrumentation; Electrocardiography / methods; Electrodes; Equipment Design; Humans; Muscle, Skeletal / physiology; Principal Component Analysis; Signal Processing, Computer-Assisted; Textiles
topics (OpenAlex): Muscle activation and electromyography studies; Advanced Sensor and Energy Harvesting Materials; EEG and Brain-Computer Interfaces
TL;DR:
It is observed that signals from the dry textile electrodes introduce less artifacts associated with muscle activation, so it is possible to obtain good performance for both the wet and dry electrodes.
(via Semantic Scholar)
Sources: NC State University Libraries, ORCID, NC State University Libraries
Added: August 6, 2018