Details

Autor(en) / Beteiligte

• Golestani, Negar
• Moghaddam, Mahta

Titel

Human activity recognition using magnetic induction-based motion signals and deep recurrent neural networks

Ist Teil von

• Nature communications, 2020-03, Vol.11 (1), p.1551-1551, Article 1551

Ort / Verlag

England: Nature Publishing Group

Erscheinungsjahr

2020

Link zum Volltext

Quelle

Elektronische Zeitschriftenbibliothek (Open access)

Beschreibungen/Notizen

• Recognizing human physical activities using wireless sensor networks has attracted significant research interest due to its broad range of applications, such as healthcare, rehabilitation, athletics, and senior monitoring. There are critical challenges inherent in designing a sensor-based activity recognition system operating in and around a lossy medium such as the human body to gain a trade-off among power consumption, cost, computational complexity, and accuracy. We introduce an innovative wireless system based on magnetic induction for human activity recognition to tackle these challenges and constraints. The magnetic induction system is integrated with machine learning techniques to detect a wide range of human motions. This approach is successfully evaluated using synthesized datasets, laboratory measurements, and deep recurrent neural networks.