Gait Parameters Analysis Based on Leg-and-shoe-mounted IMU and Deep Learning

Lin, Po-Hsin; Shih, Chang-Lin; Wong, Davy P. Y.; Chou, Pai H.

doi:10.1109/vlsi-dat52063.2021.9427325

Cited by 2 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many previous studies have looked at the use of multiple sensors to analyze gait events. Lin et al [ 22 ] used LSTM-based regression model using five IMUs, two on the thighs, two on the shins, and one on the left shoe. They achieved the mean error (ME) of 2 ms for HS; however, large errors for TO were reported with the ME of −18 ms.…”

Section: Discussionmentioning

confidence: 99%

“…The introduction of smaller, lighter, and cheaper sensors such as the inertial measurement unit (IMU) sensors made it possible to break free from the laborsome and costly ways of using motion capture systems and force-plates, which were limited to a strict clinical setting [ 15 , 16 ]. The advent of machine learning-based methods such as Hidden Markov Models (HMM) [ 17 , 18 , 19 ], and Support Vector Machines (SVM) [ 20 ], Deep CNN [ 21 ], and Recurrent Neural Networks (RNN) [ 22 ] eased the burden of gait measurement further and opened a new horizon of accurate gait assessments.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Gait Events Prediction Using Hybrid CNN-RNN-Based Deep Learning Models through a Single Waist-Worn Wearable Sensor

Arshad

Jamsrandorj

Kim

et al. 2022

Sensors

View full text Add to dashboard Cite

Elderly gait is a source of rich information about their physical and mental health condition. As an alternative to the multiple sensors on the lower body parts, a single sensor on the pelvis has a positional advantage and an abundance of information acquirable. This study aimed to improve the accuracy of gait event detection in the elderly using a single sensor on the waist and deep learning models. Data were gathered from elderly subjects equipped with three IMU sensors while they walked. The input taken only from the waist sensor was used to train 16 deep-learning models including a CNN, RNN, and CNN-RNN hybrid with or without the Bidirectional and Attention mechanism. The groundtruth was extracted from foot IMU sensors. A fairly high accuracy of 99.73% and 93.89% was achieved by the CNN-BiGRU-Att model at the tolerance window of ±6 TS (±6 ms) and ±1 TS (±1 ms), respectively. Advancing from the previous studies exploring gait event detection, the model demonstrated a great improvement in terms of its prediction error having an MAE of 6.239 ms and 5.24 ms for HS and TO events, respectively, at the tolerance window of ±1 TS. The results demonstrated that the use of CNN-RNN hybrid models with Attention and Bidirectional mechanisms is promising for accurate gait event detection using a single waist sensor. The study can contribute to reducing the burden of gait detection and increase its applicability in future wearable devices that can be used for remote health monitoring (RHM) or diagnosis based thereon.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Gait Events Prediction Using Hybrid CNN-RNN-Based Deep Learning Models through a Single Waist-Worn Wearable Sensor

Arshad

Jamsrandorj

Kim

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Being unable to utilize the temporal nature of the information in the sliding window, MLP and CNN were not able to predict Many previous studies have looked at the use of multiple sensors to analyze gait events. Lin et al [17] used LSTMbased regression model using five IMUs, two on the thighs, two on the shins, and one on the left shoe. They achieved the mean error (ME) of 2ms for HS, however large errors for TO were reported with the ME of -18ms.…”

Section: Discussionmentioning

confidence: 99%

“…The introduction of smaller, lighter, and cheaper sensors like the inertial measurement unit (IMU) sensors made it possible to break free from the laborsome and costly ways of using motion capture systems and force-plates which were limited to a strict clinical setting [10,11]. The advent of machine learning-based methods such as Hidden Markov Models (HMM) [12,13,14], and Support Vector Machines (SVM) [15], Deep CNN [16], and Recurrent Neural Networks (RNN) [17] eased the burden of gait measurement further and opened a new horizon of accurate gait assessments.…”

mentioning

confidence: 99%

Gait Events Prediction using Hybrid CNN-RNN-based Deep Learning models through a Single Waist-worn Wearable Sensor

Arshad¹,

Jamsrandorj²,

Kim³

et al. 2022

Preprint

View full text Add to dashboard Cite

Elderly gait is a source of rich information about their physical and mental health condition. As an alternative to the multiple sensors on the lower body parts, a single sensor on the pelvis has a positional advantage and an abundance of information acquirable. This study aimed to explore a way of improving the accuracy of gait event detection in the elderly using a single sensor on the waist and deep learning models. Data was gathered from elderly subjects equipped with three IMU sensors while they walked. The input was taken only from the waist sensor was used to train 16 deep-learning models including CNN, RNN, and CNN-RNN hybrid with or without the Bidirectional and Attention mechanism. The groundtruth was extracted from foot IMU sensors. Fairly high accuracy of 99.73% and 93.89% was achieved by the CNN-BiGRU-Att model at the tolerance window of ±6TS (±6ms) and ±1TS (±1ms) respectively. Advancing from the previous studies exploring gait event detection, the model showed a great improvement in terms of its prediction error having an MAE of 6.239ms and 5.24ms for HS and TO events respectively at the tolerance window of ±1TS. The results showed that the use of CNN-RNN hybrid models with Attention and Bidirectional mechanisms is promising for accurate gait event detection using a single waist sensor. The study can contribute to reducing the burden of gait detection and increase its applicability in future wearable devices that can be used for remote health monitoring (RHM) or diagnosis based thereon.

show abstract

Gait Parameters Analysis Based on Leg-and-shoe-mounted IMU and Deep Learning

Cited by 2 publications

References 14 publications

Gait Events Prediction Using Hybrid CNN-RNN-Based Deep Learning Models through a Single Waist-Worn Wearable Sensor

Gait Events Prediction Using Hybrid CNN-RNN-Based Deep Learning Models through a Single Waist-Worn Wearable Sensor

Gait Events Prediction using Hybrid CNN-RNN-based Deep Learning models through a Single Waist-worn Wearable Sensor

Contact Info

Product

Resources

About