Real-Time Hierarchical Classification of Time Series Data for Locomotion Mode Detection

Narayan, Ashwin; Reyes, Francisco Anaya; Ren, Meifeng; Huang, Yu

doi:10.1109/jbhi.2021.3106110

Cited by 13 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…F-measure performance improvements were as follows: 0.4742 to 0.9068 for DDLMI, 0.898 to 0.9441 for DeepConvLSTM, 0.8527 to 0.9557 for LSTM-CNN, and 0.8931 to 0.9617 for the proposed model (see Table 7 and Table 8 ). These results align with previous results, that highlighted high recognition accuracy in detecting human locomotor modes with IMU sensors [ 8 ]. Interestingly, when incorporating all signals from both the EMG sensors and the wearable robot, DDLMI and LSTM-CNN showed slight improvements in F-measure performance (0.97% and 0.54% increase, respectively).…”

Section: Resultssupporting

confidence: 92%

“…In a separate study aimed at identifying user-initiated locomotion motions, ref. [ 8 ] designed a DNN classifier that combined stacked causal 2D convolutional layers followed by a fully connected layer. Unlike the above studies, this study emphasized the hierarchical classification of less specific locomotor activities before more specific actions to detect transitional motions.…”

Section: Related Workmentioning

confidence: 99%

“…Studies have indicated that exoskeletons can substantially assist and lower metabolic costs during walking [ 1 , 2 ]. Numerous powered exoskeleton robots have facilitated the improvement of lower extremity movement deficits resulting from strokes [ 3 , 4 , 5 ] or injuries such as amputations [ 6 , 7 ] by applying assistive torques to the joints [ 8 ]. However, despite these successful applications, several challenges persist in developing safe and versatile control systems [ 9 ], including the identification of the wearer’s intended movement without external commands, and the autonomous transition between different activity-specific controllers.…”

Section: Introductionmentioning

confidence: 99%

“…The collected raw signals did not contain missing values. The sample size, as shown in Table4, was(23,288,780,8) for the EMG data and (832,447, 7) for the wearable robot data. The average measurement time for the collected multivariate signals was approximately 4.66 s. Among the locomotor activities, LW (approximately 4.8 s) and RA (approximately 4.9 s) took longer than the other activities, with SA and SD both taking approximately 4.6 s and RD taking the least time at 4.3 s.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot

Son,

Kang

2023

Bioengineering

View full text Add to dashboard Cite

This study introduces a novel convolutional neural network (CNN) architecture, encompassing both single and multi-head designs, developed to identify a user’s locomotion activity while using a wearable lower limb robot. Our research involved 500 healthy adult participants in an activities of daily living (ADL) space, conducted from 1 September to 30 November 2022. We collected prospective data to identify five locomotion activities (level ground walking, stair ascent/descent, and ramp ascent/descent) across three terrains: flat ground, staircase, and ramp. To evaluate the predictive capabilities of the proposed CNN architectures, we compared its performance with three other models: one CNN and two hybrid models (CNN-LSTM and LSTM-CNN). Experiments were conducted using multivariate signals of various types obtained from electromyograms (EMGs) and the wearable robot. Our results reveal that the deeper CNN architecture significantly surpasses the performance of the three competing models. The proposed model, leveraging encoder data such as hip angles and velocities, along with postural signals such as roll, pitch, and yaw from the wearable lower limb robot, achieved superior performance with an inference speed of 1.14 s. Specifically, the F-measure performance of the proposed model reached 96.17%, compared to 90.68% for DDLMI, 94.41% for DeepConvLSTM, and 95.57% for LSTM-CNN, respectively.

show abstract

Section: Resultssupporting

confidence: 92%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot

Son,

Kang

2023

Bioengineering

View full text Add to dashboard Cite

show abstract

“…For instance, recurrent neural networks (RNN) and the long short-term memory (LSTM) are among the most promising models since they can obtain excellent performance in learning time-series signals (Wang et al, 2018 ; Lu et al, 2020a ). The convolutional neural network (CNN) has been employed regularly for terrain mode classification and human activity recognition because it could learn features automatically from simple to complex data by complicated layer-by-layer structures, also from raw sensor signal inputs (Su et al, 2019 ; Lu et al, 2020b ; Tiwari and Joshi, 2020 ; Narayan et al, 2021 ). Tables 4, 5 show the categorization of existing studies that used basic machine learning and deep learning models based on an outline of the material and methods and the accuracies of these studies.…”

Section: Introductionmentioning

confidence: 99%

Comparison of machine learning and deep learning-based methods for locomotion mode recognition using a single inertial measurement unit

Cao

Dong

et al. 2022

Front. Neurorobot.

View full text Add to dashboard Cite

Locomotion mode recognition provides the prosthesis control with the information on when to switch between different walking modes, whereas the gait phase detection indicates where we are in the gait cycle. But powered prostheses often implement a different control strategy for each locomotion mode to improve the functionality of the prosthesis. Existing studies employed several classical machine learning methods for locomotion mode recognition. However, these methods were less effective for data with complex decision boundaries and resulted in misclassifications of motion recognition. Deep learning-based methods potentially resolve these limitations as it is a special type of machine learning method with more sophistication. Therefore, this study evaluated three deep learning-based models for locomotion mode recognition, namely recurrent neural network (RNN), long short-term memory (LSTM) neural network, and convolutional neural network (CNN), and compared the recognition performance of deep learning models to the machine learning model with random forest classifier (RFC). The models are trained from data of one inertial measurement unit (IMU) placed on the lower shanks of four able-bodied subjects to perform four walking modes, including level ground walking (LW), standing (ST), and stair ascent/stair descent (SA/SD). The results indicated that CNN and LSTM models outperformed other models, and these models were promising for applying locomotion mode recognition in real-time for robotic prostheses.

show abstract

Deep learning based ankle–foot movement classification for prosthetic foot

Aydin Fandakli,

Okumus

2024

Neural Comput & Applic

View full text Add to dashboard Cite

The primary motivation behind this study is the aspiration to design a prosthetic foot that demonstrates enhanced functionality, enabling more active and prompt responses, particularly tailored for individuals with below-knee amputations. This goal underscores the intention to create a prosthetic foot with the capability to execute foot movements in a more natural and effective manner. A new 1D-ResCNN model has been proposed for the rapid and accurate classification of foot movements based on user intent in the context of a prosthetic limb. This research introduces an innovative approach by integrating inertial measurement units with deep learning algorithms to advance the development of more functional prosthetic feet, specifically tailored for below-knee amputees. Leveraging wearable technologies, this method allows for the prolonged monitoring of foot movements within the users’ natural environments. The dual benefits of cost reduction and enhanced user experience are achieved through this combination of advanced technologies, providing a promising avenue for the evolution of prosthetic foot design and usage. The results obtained with this model are satisfying both in terms of speed and accuracy with 99.8% compared to other methods in the literature.

show abstract

Real-Time Hierarchical Classification of Time Series Data for Locomotion Mode Detection

Cited by 13 publications

References 42 publications

Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot

Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot

Comparison of machine learning and deep learning-based methods for locomotion mode recognition using a single inertial measurement unit

Deep learning based ankle–foot movement classification for prosthetic foot

Contact Info

Product

Resources

About