Determining motions with an IMU during level walking and slope and stair walking

Chen, Wei-Han; Lee, Yin Shin; Yang, Ching Jui; Chang, Su Yu; Shih, Yo; Sui, Jien-De; Chang, Tian-Sheuan; Shiang, Tzyy Yuang

doi:10.1080/02640414.2019.1680083

Cited by 21 publications

(23 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep belief networks (DBNs) are used on features in the time-frequency domain of a triaxial accelerometer to recognize (loco)motion modes of both healthy and impaired subjects in [13], while a convolutional neural network (CNN) is used on time domain features of a triaxial accelerometer to recognize locomotion modes of healthy subjects in [14]. CNNs are used on raw-data from one IMU placed on the foot to recognize locomotion modes of healthy subjects in [15], on raw-data from multiple IMUs on the lower limbs to predict locomotion modes of healthy subjects in [16], on rawdata from multiple IMUs on the lower limbs to recognize both the locomotion modes and the transitions of healthy subjects and transtibial amputees in [17], on raw-data from multiple IMUs on the lower-limbs and/or torso to recognize locomotion modes of healthy subjects in [18], on IMU features in the time-frequency domain to recognize (loco)motion modes on healthy subjects in [19], [20], [21], and on features in the timefrequency domain of an accelerometer to recognize locomotion modes on healthy subjects in [21]. Recurrent neural networks (RNNs) have also been used to learn IMUs features.…”

Section: Introductionmentioning

confidence: 99%

IMU-Based Deep Neural Networks: Prediction of Locomotor and Transition Intentions of an Osseointegrated Transfemoral Amputee

Bruinsma

Carloni

2021

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

This paper focuses on the design and comparison of different deep neural networks for the real-time prediction of locomotor and transition intentions of one osseointegrated transfemoral amputee using only data from inertial measurement units. The deep neural networks are based on convolutional neural networks, recurrent neural networks, and convolutional recurrent neural networks. The architectures' input are features in both the time domain and the time-frequency domain, which are derived from either one inertial measurement unit (placed above the prosthetic knee) or two inertial measurement units (placed above and below the prosthetic knee). The prediction of eight different locomotion modes (i.e., sitting, standing, level ground walking, stair ascent and descent, ramp ascent and descent, walking on uneven terrain) and the twenty-four transitions among them is investigated. The study shows that a recurrent neural network, realized with four layers of gated recurrent unit networks, achieves (with a 5-fold cross-validation) a mean F1 score of 84.78% and 86.50% using one inertial measurement unit, and 93.06% and 89.99% using two inertial measurement units, with or without sitting, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

IMU-Based Deep Neural Networks: Prediction of Locomotor and Transition Intentions of an Osseointegrated Transfemoral Amputee

Bruinsma

Carloni

2021

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…IMU features learning, by means of deep learning methods, has also been recently used for locomotion mode recognition and locomotion intent prediction. For example, deep belief networks have been used in combination with the spectrogram of one accelerometer sensor [10], Convolutional Neural Networks (CNNs) with one IMU on the foot [11], [12], CNN with several IMUs placed at different locations on the lower-limbs and torso [13], [14], [15], Recurrent Neural Network (RNN) with one IMU on the lower back [16].…”

Section: Introductionmentioning

confidence: 99%

IMU-based Deep Neural Networks for Locomotor Intention Prediction

Schomaker

Carloni

2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

This paper focuses on the design and comparison of different deep neural networks for the real-time prediction of locomotor intentions by using data from inertial measurement units. The deep neural network architectures are convolutional neural networks, recurrent neural networks, and convolutional recurrent neural networks. The input to the architectures are features in the time domain, which have been derived either from one inertial measurement unit placed on the upper right leg of ten healthy subjects, or two inertial measurement units placed on both the upper and lower right leg of ten healthy subjects. The study shows that a WaveNet, i.e., a full convolutional neural network, achieves a peak F1-score of 87.17% in the case of one IMU, and a peak of 97.88% in the case of two IMUs, with a 5-fold cross-validation.

show abstract

“…In the context of HAR for detection of stair climbing, approaches mainly differ for the sensing modality, position of the sensor/s, features, algorithms used for classification, and target users. Sensors comprise IMUs [5,[12][13][14][15] and their combined use with barometers [16][17][18][19][20][21]. Positions include wrist [16,17], chest [16,18,20], waist [5,12,17,19], calf and foot [13][14][15][16]21].…”

Section: Introductionmentioning

confidence: 99%

“…Sensors comprise IMUs [5,[12][13][14][15] and their combined use with barometers [16][17][18][19][20][21]. Positions include wrist [16,17], chest [16,18,20], waist [5,12,17,19], calf and foot [13][14][15][16]21]. Common features are averages, ranges, Fourier Transform and Wavelet coefficients, statistical moments of sensor data, whereas classifiers are Support Vector Machine (SVM) [5,12,16,17,19], K-Nearest Neighbour (KNN) [5,16,17], Decision Tree and Random Forest [5,13,17,19], Artificial Neural Network (ANN) [22], and also convolutional NN [15].…”

Section: Introductionmentioning

confidence: 99%

“…Positions include wrist [16,17], chest [16,18,20], waist [5,12,17,19], calf and foot [13][14][15][16]21]. Common features are averages, ranges, Fourier Transform and Wavelet coefficients, statistical moments of sensor data, whereas classifiers are Support Vector Machine (SVM) [5,12,16,17,19], K-Nearest Neighbour (KNN) [5,16,17], Decision Tree and Random Forest [5,13,17,19], Artificial Neural Network (ANN) [22], and also convolutional NN [15]. Users span from healthy young people up to elderly patients with severe conditions such as Parkinson's disease or stroke [5,16,20].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Design and Validation of a Minimal Complexity Algorithm for Stair Step Counting

et al. 2020

View full text Add to dashboard Cite

Wearable sensors play a significant role for monitoring the functional ability of the elderly and in general, promoting active ageing. One of the relevant variables to be tracked is the number of stair steps (single stair steps) performed daily, which is more challenging than counting flight of stairs and detecting stair climbing. In this study, we proposed a minimal complexity algorithm composed of a hierarchical classifier and a linear model to estimate the number of stair steps performed during everyday activities. The algorithm was calibrated on accelerometer and barometer recordings measured using a sensor platform worn at the wrist from 20 healthy subjects. It was then tested on 10 older people, specifically enrolled for the study. The algorithm was then compared with other three state-of-the-art methods, which used the accelerometer, the barometer or both. The experiments showed the good performance of our algorithm (stair step counting error: 13.8%), comparable with the best state-of-the-art (p > 0.05), but using a lower computational load and model complexity. Finally, the algorithm was successfully implemented in a low-power smartwatch prototype with a memory footprint of about 4 kB.

show abstract

Determining motions with an IMU during level walking and slope and stair walking

Cited by 21 publications

References 27 publications

IMU-Based Deep Neural Networks: Prediction of Locomotor and Transition Intentions of an Osseointegrated Transfemoral Amputee

IMU-Based Deep Neural Networks: Prediction of Locomotor and Transition Intentions of an Osseointegrated Transfemoral Amputee

IMU-based Deep Neural Networks for Locomotor Intention Prediction

Design and Validation of a Minimal Complexity Algorithm for Stair Step Counting

Contact Info

Product

Resources

About