Cross-Subject and Cross-Modal Transfer for Generalized Abnormal Gait Pattern Recognition

Gu, Xiao; Guo, Yao; Deligianni, Fani; Lo, Benny; Yang, Guang‐Zhong

doi:10.1109/tnnls.2020.3009448

Cited by 43 publications

(23 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, spatiotemporal parameters, especially in pwMS with mild disabilities are often similar to those in healthy individuals, and the differences only become visible with special processing techniques. An evaluation of video-based data was not possible for precise classification of gait patterns, even though it is continuously developed and proved to be a very reliable tool for gait analysis [90].…”

Section: Discussionmentioning

confidence: 99%

Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple Sclerosis

et al. 2021

View full text Add to dashboard Cite

In multiple sclerosis (MS), gait impairment is one of the most prominent symptoms. For a sensitive assessment of pathological gait patterns, a comprehensive analysis and processing of several gait analysis systems is necessary. The objective of this work was to determine the best diagnostic gait system (DIERS pedogait, GAITRite system, and Mobility Lab) using six machine learning algorithms for the differentiation between people with multiple sclerosis (pwMS) and healthy controls, between pwMS with and without fatigue and between pwMS with mild and moderate impairment. The data of the three gait systems were assessed on 54 pwMS and 38 healthy controls. Gaussian Naive Bayes, Decision Tree, k-Nearest Neighbor, and Support Vector Machines (SVM) with linear, radial basis function (rbf) and polynomial kernel were applied for the detection of subtle walking changes. The best performance for a healthy-sick classification was achieved on the DIERS data with a SVM rbf kernel (k = 0.49 ± 0.11). For differentiating between pwMS with mild and moderate disability, the GAITRite data with the SVM linear kernel (k = 0.61 ± 0.06) showed the best performance. This study demonstrates that machine learning methods are suitable for identifying pathologic gait patterns in early MS.

show abstract

Section: Discussionmentioning

confidence: 99%

Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple Sclerosis

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Indeed, source data selection is an important problem in transfer learning [8,27], which warrants future investigation. For example, the analysis approach taken in this work provides a framework in which one can systematically assess source data selection, as well as combine the effects of transfer learning across contexts (e.g., user × day) using layers of domain adversarial networks [40].…”

Section: Discussionmentioning

confidence: 99%

Feasibility of Using Wearable EMG Armbands combined with Unsupervised Transfer Learning for Seamless Myoelectric Control

Sohn

Lai

Elwin

et al. 2022

Preprint

View full text Add to dashboard Cite

Myoelectric control uses electromyography (EMG) signals as human-originated input to enable intuitive interfaces with machines. As such, recent rehabilitation robotics employs myoelectric control to autonomously classify user intent or operation mode using machine learning. However, performance in such applications inherently suffers from the non-stationarity of EMG signals across measurement conditions. Current laboratory-based solutions rely on careful, time-consuming control of the recordings or periodic recalibration, impeding real-world deployment. We propose that robust yet seamless myoelectric control can be achieved using a low-end, easy-to-don and doff wearable EMG sensor combined with unsupervised transfer learning. Here, we test the feasibility of one such application using a consumer-grade sensor (Myo armband, 8 EMG channels @ 200 Hz) for gesture classification across measurement conditions using an existing dataset: 5 users x 10 days x 3 sensor locations. Specifically, we first train a deep neural network using Temporal-Spatial Descriptors (TSD) with labeled source data from any particular user, day, or location. We then apply the Self-Calibrating Asynchronous Domain Adversarial Neural Network (SCADANN), which automatically adjusts the trained TSD to improve classification performance for unlabeled target data from a different user, day, or sensor location. Compared to the original TSD, SCADANN improves accuracy by 12±5.2% (avg±sd), 9.6±5.0%, and 8.6±3.3% across all possible user-to-user, day-to-day, and location-to-location cases, respectively. In one best-case scenario, accuracy improves by 26% (from 67% to 93%), whereas sometimes the gain is modest (e.g., from 76% to 78%). We also show that the performance of transfer learning can be improved by using a better model trained with good (e.g., incremental) source data. We postulate that the proposed approach is feasible and promising and can be further tailored for seamless myoelectric control of powered prosthetics or exoskeletons.

show abstract

“…For the design of our perception system, we consider therefore HMMs as a core method for coping with the targeted dynamic process, which is inherently stochastic and only partially observable. Similar work can be found in the area of robotics with promising results [47,48]. As a special type of Bayesian Inference (BI) [46,49], HMM is widely used in speech recognition [50,51], natural language modeling [52], on-line handwriting recognition [53], and for the analysis of biological sequences such as proteins and DNA [54,55].…”

Section: Related Workmentioning

confidence: 98%

Analyzing Dynamic Operational Conditions of Limb Prosthetic Sockets with a Mechatronics-Twin Framework

Chen

Ottikkutti

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

Lower limb prostheses offer a solution to restore the ambulation and self-esteem of amputees. One key component is the prosthetic socket that serves as the interface between prosthetic device and amputee stump and thereby has a wide range of impacts on efficient fitting, appropriate load transmission, operational stability, and control. For the design and optimization of a prosthetic socket, an understanding of the actual intra-socket operational conditions becomes therefore necessary. This is however a difficult task due to the inherent complexity and restricted observability of socket operation. In this study, an innovative mechatronics-twin framework that integrates advanced biomechanical models and simulations with physical prototyping and dynamic operation testing for effective exploration of operational behaviors of prosthetic sockets with amputees is proposed. Within this framework, a specific Stewart manipulator is developed to enable dynamic operation testing, in particular for a well-managed generation of dynamic intra-socket loads and behaviors that are otherwise difficult to observe or realize with the real amputees. A combination of deep learning and Bayesian Inference algorithms is then employed for analyzing the intra-socket load conditions and revealing possible anomalous.

show abstract

Cross-Subject and Cross-Modal Transfer for Generalized Abnormal Gait Pattern Recognition

Cited by 43 publications

References 53 publications

Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple Sclerosis

Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple Sclerosis

Feasibility of Using Wearable EMG Armbands combined with Unsupervised Transfer Learning for Seamless Myoelectric Control

Analyzing Dynamic Operational Conditions of Limb Prosthetic Sockets with a Mechatronics-Twin Framework

Contact Info

Product

Resources

About