Stride Segmentation during Free Walk Movements Using  Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor Data

Barth, Jens; Oberndorfer, Cäcilia; Pasluosta, Cristian; Schülein, Samuel; Gaßner, Heiko; Reinfelder, Samuel; Kugler, Patrick; Schuldhaus, Dominik; Winkler, Jürgen; Klucken, Jochen; Eskofier, Bjoern M.

doi:10.3390/s150306419

Cited by 166 publications

(207 citation statements)

References 31 publications

Supporting

Mentioning

202

Contrasting

Order By: Relevance

“…Detection of these two events within the sensor data is done according to [10]. We call the stride definition provided by the dataset msDTW because of the multi-dimensional subsequence dynamic time warping they used for segmentation (for details see [10], [40]). An exemplary, pre-processed input signal for the network for one stride defined from MS→MS is shown in Fig.…”

Section: A) Data Collection and Setupmentioning

confidence: 99%

Mobile Stride Length Estimation With Deep Convolutional Neural Networks

Hannink¹,

Kautz²,

Pasluosta³

et al. 2018

IEEE J. Biomed. Health Inform.

Self Cite

107

View full text Add to dashboard Cite

Abstract-Objective: Accurate estimation of spatial gait characteristics is critical to assess motor impairments resulting from neurological or musculoskeletal disease. Currently, however, methodological constraints limit clinical applicability of stateof-the-art double integration approaches to gait patterns with a clear zero-velocity phase. Methods: We describe a novel approach to stride length estimation that uses deep convolutional neural networks to map stride-specific inertial sensor data to the resulting stride length. The model is trained on a publicly available and clinically relevant benchmark dataset consisting of 1220 strides from 101 geriatric patients. Evaluation is done in a 10-fold cross validation and for three different stride definitions.Results: Even though best results are achieved with strides defined from mid-stance to mid-stance with average accuracy and precision of 0.01±5.37 cm, performance does not strongly depend on stride definition. The achieved precision outperforms stateof-the-art methods evaluated on the same benchmark dataset by 3.0 cm (36%). Conclusion: Due to the independence of stride definition, the proposed method is not subject to the methodological constrains that limit applicability of state-of-the-art double integration methods. Furthermore, it was possible to improve precision on the benchmark dataset. Significance: With more precise mobile stride length estimation, new insights to the progression of neurological disease or early indications might be gained. Due to the independence of stride definition, previously uncharted diseases in terms of mobile gait analysis can now be investigated by re-training and applying the proposed method.

show abstract

Section: A) Data Collection and Setupmentioning

confidence: 99%

Mobile Stride Length Estimation With Deep Convolutional Neural Networks

Hannink¹,

Kautz²,

Pasluosta³

et al. 2018

IEEE J. Biomed. Health Inform.

Self Cite

107

View full text Add to dashboard Cite

show abstract

“…These can be facilitated by simplistic approaches such as peak detection or zero-crossings [36], or sequential model-based approaches such as hidden Markov models [37]. Template-based approaches, such as longest common subsequence [38], Dynamic Time Warping [39], and the multi-dimensional subsequence Dynamic Time Warping approach (msDTW) [40] are also commonly used. The aforementioned methods are often chosen and optimized depending on the application context, as they vary in computational complexity for training, effectiveness, and generality.…”

Section: Segmentationmentioning

confidence: 99%

“…In [30], several approaches are reported, including Euclidean distance and correlation coefficients [57]. A more sophisticated method is template matching, where Dynamic Time Warping is often adopted [39].…”

Section: Recognition Of Important Gait Eventsmentioning

confidence: 99%

An Overview of Smart Shoes in the Internet of Health Things: Gait and Mobility Assessment in Health Promotion and Disease Monitoring

et al. 2017

Self Cite

View full text Add to dashboard Cite

New smart technologies and the internet of things increasingly play a key role in healthcare and wellness, contributing to the development of novel healthcare concepts. These technologies enable a comprehensive view of an individual's movement and mobility, potentially supporting healthy living as well as complementing medical diagnostics and the monitoring of therapeutic outcomes. This overview article specifically addresses smart shoes, which are becoming one such smart technology within the future internet of health things, since the ability to walk defines large aspects of quality of life in a wide range of health and disease conditions. Smart shoes offer the possibility to support prevention, diagnostic work-up, therapeutic decisions, and individual disease monitoring with a continuous assessment of gait and mobility. This overview article provides the technological as well as medical aspects of smart shoes within this rising area of digital health applications, and is designed especially for the novel reader in this specific field. It also stresses the need for closer interdisciplinary interactions between technological and medical experts to bridge the gap between research and practice. Smart shoes can be envisioned to serve as pervasive wearable computing systems that enable innovative solutions and services for the promotion of healthy living and the transformation of health care.

show abstract

“…Jochen Klucken et al [24] were able to successfully distinguish PD patients from healthy subjects with an accuracy of 81%. Jens Barth et al [25] have presented a methodology to search for patterns matching a pre-defined stride template from footwear sensor data, to automatically segment single strides from continuous movement sequences.…”

Section: Gait Analysismentioning

confidence: 99%

A Comparative Review of Footwear-Based Wearable Systems

2016

View full text Add to dashboard Cite

Abstract:Footwear is an integral part of daily life. Embedding sensors and electronics in footwear for various different applications started more than two decades ago. This review article summarizes the developments in the field of footwear-based wearable sensors and systems. The electronics, sensing technologies, data transmission, and data processing methodologies of such wearable systems are all principally dependent on the target application. Hence, the article describes key application scenarios utilizing footwear-based systems with critical discussion on their merits. The reviewed application scenarios include gait monitoring, plantar pressure measurement, posture and activity classification, body weight and energy expenditure estimation, biofeedback, navigation, and fall risk applications. In addition, energy harvesting from the footwear is also considered for review. The article also attempts to shed light on some of the most recent developments in the field along with the future work required to advance the field.

show abstract

Stride Segmentation during Free Walk Movements Using Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor Data

Cited by 166 publications

References 31 publications

Mobile Stride Length Estimation With Deep Convolutional Neural Networks

Mobile Stride Length Estimation With Deep Convolutional Neural Networks

An Overview of Smart Shoes in the Internet of Health Things: Gait and Mobility Assessment in Health Promotion and Disease Monitoring

A Comparative Review of Footwear-Based Wearable Systems

Contact Info

Product

Resources

About