A Platform for Free-Weight Exercise Monitoring with Passive Tags

Ding, Han; Han, Jinsong; Shangguan, Longfei; Xi, Wei; Jiang, Zhiping; Yang, Zheng; Zhou, Zimu; Yang, Panlong; Zhao, Jizhong

doi:10.1109/tmc.2017.2691705

Cited by 85 publications

(58 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Skinput [10] uses a wearable bioacoustic sensor array to analyze the mechanical vibrations that travel in the body to identify the movement of the arms and fingers. FEMO [11] is a human motion detection system based on RFID, which uses the backscattering signal of the passive RFID tag installed on the training equipment to detect the motion state of the user. eFisio-Track [12] is a telemedicine assistance system that detects patients' rehabilitation training movements by using the accelerometer equipment.…”

Section: Device-based Human Motion Recognitionmentioning

confidence: 99%

CSI-HC: A WiFi-Based Indoor Complex Human Motion Recognition Method

Hao

Duan

Dang

et al. 2020

Mobile Information Systems

View full text Add to dashboard Cite

WiFi indoor personnel behavior recognition has become the core technology of wireless network perception. However, the existing human behavior recognition methods have great challenges in terms of detection accuracy, intrusion, and complexity of operations. In this paper, we firstly analyze and summarize the existing human motion recognition schemes, and due to the existence of the problems in them, we propose a noninvasive, highly robust complex human motion recognition scheme based on Channel State Information (CSI), that is, CSI-HC, and the traditional Chinese martial art XingYiQuan is verified as a complex motion background. CSI-HC is divided into two phases: offline and online. In the offline phase, the human motion data are collected on the commercial Atheros NIC and a powerful denoising method is constructed by using the Butterworth low-pass filter and wavelet function to filter the outliers in the motion data. Then, through Restricted Boltzmann Machine (RBM) training and classification, we establish offline fingerprint information. In the online phase, SoftMax regression is used to correct the RBM classification to process the motion data collected in real time and the processed real-time data are matched with the offline fingerprint information. On this basis, the recognition of a complex human motion is realized. Finally, through repeated experiments in three classical indoor scenes, the parameter setting and user diversity affecting the accuracy of motion recognition are analyzed and the robustness of CSI-HC is detected. In addition, the performance of the proposed method is compared with that of the existing motion recognition methods. The experimental results show that the average motion recognition rate of CSI-HC in three classic indoor scenes reaches 85.4%, in terms of motion complexity and indoor recognition accuracy. Compared with other algorithms, it has higher stability and robustness.

show abstract

Section: Device-based Human Motion Recognitionmentioning

confidence: 99%

CSI-HC: A WiFi-Based Indoor Complex Human Motion Recognition Method

Hao

Duan

Dang

et al. 2020

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…Sliding window approaches (1) move a window of static size sequentially across an incoming stream of data and extract the window's current content for further analysis. E.g., authors of RecoFit and ClimbAX used a 5s sliding window which they moved in discrete steps across a motion data stream [5], [6], [7]. These approaches offer valuable ideas for our segmentation concept.…”

Section: Related Workmentioning

confidence: 99%

Qualitative assessment of recurrent human motion

Ebert

Beck

Mattausch

et al. 2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Abstract-Smartphone applications designed to track human motion in combination with wearable sensors, e.g., during physical exercising, raised huge attention recently. Commonly, they provide quantitative services, such as personalized training instructions or the counting of distances. But qualitative monitoring and assessment is still missing, e.g., to detect malpositions, to prevent injuries, or to optimize training success.We address this issue by presenting a concept for qualitative as well as generic assessment of recurrent human motion by processing multi-dimensional, continuous time series tracked with motion sensors. Therefore, our segmentation procedure extracts individual events of specific length and we propose expressive features to accomplish a qualitative motion assessment by supervised classification. We verified our approach within a comprehensive study encompassing 27 athletes undertaking different body weight exercises. We are able to recognize six different exercise types with a success rate of 100% and to assess them qualitatively with an average success rate of 99.3%.

show abstract

“…MyoVibe [11] leverages mechanomyogram (MMG) sensors to sense muscle activation for session segmentation. Repetitions can be counted by processing inertial sensor signals [3,14,16] or observing the Doppler Effect from RFID sensors [10]. Prior work also explored exercise type recognition through machine learning algorithms [7,20].…”

Section: Related Workmentioning

confidence: 99%

MyoBuddy

Liu

Tseng

et al. 2017

Proceedings of the 1st Workshop on Digital Biomarkers

View full text Add to dashboard Cite

Muscular dystrophy is a group of genetic diseases that cause the loss of muscles and hence weakening the muscle strength. A typical treatment for muscular dystrophy patients is routinely performing weight exercise to slow down the loss in muscles. Thus, we propose a system MyoBuddy to help both physical therapists and patients to keep track of the weights in workout activities based on electromyography (EMG) sensors embedded in Myo armband. In our study, we collect 102 sessions of EMG data from barbell bicep curl exercise with a range of weights from 20 to 70 lbs with a 10-pound increment. Both Support Vector Machine and Random Forest algorithms are explored to classify which weight of barbells are lifted. At the end, we achieve 77.1% classification accuracy on average. † Equal contribution authors 1 The source of the statistics: https://www.cdc.gov/ ncbddd/musculardystrophy/research.html

show abstract

A Platform for Free-Weight Exercise Monitoring with Passive Tags

Cited by 85 publications

References 26 publications

CSI-HC: A WiFi-Based Indoor Complex Human Motion Recognition Method

CSI-HC: A WiFi-Based Indoor Complex Human Motion Recognition Method

Qualitative assessment of recurrent human motion

MyoBuddy

Contact Info

Product

Resources

About