Wearable Biofeedback Suit to Promote and Monitor Aquatic Exercises: A Feasibility Study

Gandolla, Marta; Pedrocchi, Alessandra; Ferrante, S.; Andrea, Costa; Bortolotti, Dario; Sorti, Stefano; Federico, Vitale; Bocciolone, M.; Braghin, Francesco; Masiero, Stefano

doi:10.1109/tim.2019.2911756

Cited by 35 publications

(31 citation statements)

References 40 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparing to the dual-IMU based systems, they have more three-dimensional measurement points attached on the human body parts. Thus, the multi-IMU based systems are capable of providing more accurate measurement for various complex body movements [19].…”

Section: Related Workmentioning

confidence: 99%

On-Device Lumbar-Pelvic Movement Detection Using Dual-IMU: A DNN-Based Approach

et al. 2021

View full text Add to dashboard Cite

Lumbar-pelvic movements (LPMs) are generally performed in the clinical setting to identify limitations in a range of movements. Continuous monitoring of these movements can provide real-time feedback to both patients and medical experts with the potential of identifying activities that may precipitate symptoms of low back pain (LBP) as well as improving therapy by providing a personalised approach. Recent advances in mobile computing technology and wearable sensors have paved the way for developing mobile physical activity monitoring applications with more advanced and complex algorithms, such as deep neural network (DNN) based models. However, there is a lack of prior studies that focus on real-time LPMs detection with multimodal sensory data. Meanwhile, most research in the area of body movement detection do not consider the potential transition logic of the constituent low-level body movements (e.g., LPMs) within their corresponding high-level physical activity. This information could significantly increase accuracy of detection results. Further, current studies mainly perform deep learning-based movement detection in the cloud (or a backend server) that could increase network bandwidth and response time.To address these limitations, this paper proposes a novel LPMs detection approach using an enhanced and adapted hybrid DNN model, which includes a convolutional neural network followed by a long-short term memory recurrent network (CNN-LSTM), and performs detection locally on the mobile device. The results of a comparative evaluation of the proposed model and baseline models are described. We also introduce a set of domain-specific pre-defined rules, based on the transition logic information, to reconstruct the detection outputs to further improve the detection accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

On-Device Lumbar-Pelvic Movement Detection Using Dual-IMU: A DNN-Based Approach

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In order to objectively acquire key points of target movements from video, several novel methods have been proposed for acquiring coordinates of the points based on physically measured data from sensor devices or optical sensors. The researches [ 14 , 15 ] are the typical trials for measuring the body movements numerically. Furthermore, there are advanced researches that apply measure sports activities via sensors.…”

Section: Backgrounds and Definitionsmentioning

confidence: 99%

Statistical Extraction Method for Revealing Key Factors from Posture before Initiating Successful Throwing Technique in Judo

Kato

Yamagiwa

2021

Sensors

View full text Add to dashboard Cite

Many methods such as biomechanics and coaching have been proposed to help people learn a certain movement. There have been proposals for methods to discover characteristics of movement based on information obtained from videos and sensors. Especially in sports, it is expected that these methods can provide hints to improve movement skills. However, conventional methods focus on individual movements, and do not consider cases where external factors influence the movement, such as combat sports. In this paper, we propose a novel method called the Extraction for Successful Movement method (XSM method). Applying the method, this paper focuses on throwing techniques in judo to discover key factors that induce successful throwing from the postures right before initiating the throwing techniques. We define candidate factors by observing the video scenes where the throwing techniques are successfully performed. The method demonstrates the significance of the key factors according to the predominance of factors by χ2 test and residual analysis. Applying the XSM method to the dataset obtained from the videos of the Judo World Championships, we demonstrate the validity of the method with discussing the key factors related to the successful throwing techniques.

show abstract

“…The fidelity of motion kinematics obtained from IMC systems has been previously verified [7][8][9][10][11][12][13]. Currently available IMC systems have been used in different domains for various applications, including activity recognition [14][15][16] and activity assessments [17][18][19]. Marta et al [17] developed a wearable biofeedback suit equipped with 10 IMUs.…”

Section: Introductionmentioning

confidence: 99%

Inertial Motion Capture-Based Whole-Body Inverse Dynamics

Diraneyya

Ryu

Abdel‐Rahman

et al. 2021

Sensors

View full text Add to dashboard Cite

Inertial Motion Capture (IMC) systems enable in situ studies of human motion free of the severe constraints imposed by Optical Motion Capture systems. Inverse dynamics can use those motions to estimate forces and moments developing within muscles and joints. We developed an inverse dynamic whole-body model that eliminates the usage of force plates (FPs) and uses motion patterns captured by an IMC system to predict the net forces and moments in 14 major joints. We validated the model by comparing its estimates of Ground Reaction Forces (GRFs) to the ground truth obtained from FPs and comparing predictions of the static model’s net joint moments to those predicted by 3D Static Strength Prediction Program (3DSSPP). The relative root-mean-square error (rRMSE) in the predicted GRF was 6% and the intraclass correlation of the peak values was 0.95, where both values were averaged over the subject population. The rRMSE of the differences between our model’s and 3DSSPP predictions of net L5/S1 and right and left shoulder joints moments were 9.5%, 3.3%, and 5.2%, respectively. We also compared the static and dynamic versions of the model and found that failing to account for body motions can underestimate net joint moments by 90% to 560% of the static estimates.

show abstract

Wearable Biofeedback Suit to Promote and Monitor Aquatic Exercises: A Feasibility Study

Cited by 35 publications

References 40 publications

On-Device Lumbar-Pelvic Movement Detection Using Dual-IMU: A DNN-Based Approach

On-Device Lumbar-Pelvic Movement Detection Using Dual-IMU: A DNN-Based Approach

Statistical Extraction Method for Revealing Key Factors from Posture before Initiating Successful Throwing Technique in Judo

Inertial Motion Capture-Based Whole-Body Inverse Dynamics

Contact Info

Product

Resources

About