Monitoring of gait performance using dynamic time warping on IMU-sensor data

Wang, Xingchen; Kyrarini, Maria; Ristić-Durrant, Danijela; Spranger, Matthias; Gräser, Axel

doi:10.1109/memea.2016.7533745

Cited by 19 publications

(18 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sensors are the fundamental elements of a joint monitoring system to measure the physiological parameters—angle, range of motion and posture—of joints. Various research groups [16,17,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82] have used different sensor types to build joint monitoring systems. Some systems were developed using a single sensor; others were assembled with a combination of multiple sensor technologies using data fusion methods.…”

Section: Sensors and Technologiesmentioning

confidence: 99%

Monitoring Methods of Human Body Joints: State-of-the-Art and Research Challenges

Faisal

Majumder

Mondal

et al. 2019

Sensors

126

100

View full text Add to dashboard Cite

The world’s population is aging: the expansion of the older adult population with multiple physical and health issues is now a huge socio-economic concern worldwide. Among these issues, the loss of mobility among older adults due to musculoskeletal disorders is especially serious as it has severe social, mental and physical consequences. Human body joint monitoring and early diagnosis of these disorders will be a strong and effective solution to this problem. A smart joint monitoring system can identify and record important musculoskeletal-related parameters. Such devices can be utilized for continuous monitoring of joint movements during the normal daily activities of older adults and the healing process of joints (hips, knees or ankles) during the post-surgery period. A viable monitoring system can be developed by combining miniaturized, durable, low-cost and compact sensors with the advanced communication technologies and data processing techniques. In this study, we have presented and compared different joint monitoring methods and sensing technologies recently reported. A discussion on sensors’ data processing, interpretation, and analysis techniques is also presented. Finally, current research focus, as well as future prospects and development challenges in joint monitoring systems are discussed.

show abstract

Section: Sensors and Technologiesmentioning

confidence: 99%

Monitoring Methods of Human Body Joints: State-of-the-Art and Research Challenges

Faisal

Majumder

Mondal

et al. 2019

Sensors

126

100

View full text Add to dashboard Cite

show abstract

“…The second database comes from the data of gait signal [3] from Institute of Automation, University of Bremen. In this test, thesignal vector magnitude of acceleration gait signal with sampling rate of 30 Hz is segmented [10].…”

Section: Performance Analysismentioning

confidence: 99%

“…As a newly developed research area, gait analysis has shown great potential for diagnosis in neurodegenerative diseases such as Parkinson's disease or peripheral neuropathy. Different systems are used in order to obtain gait signals, such as vision-based systems [1], goniometers [2], Inertial Measurement Units (IMUs) [3], foot pressure sensors [4]. Gait data are commonly recorded at different parts of human body, such as lower limbs, feet, and lower waist.…”

Section: Introductionmentioning

confidence: 99%

“…Gait data are commonly recorded at different parts of human body, such as lower limbs, feet, and lower waist. Important gait features are usually extracted from individual gait cycle for the purpose of clinical gait assessment and monitoring [3].In order to enable gait analysis based on gait cycles, segmentation of gait cycle from a dataset containing multiple cycles is needed. One gait cycle is defined as the interval between two successive heel stride incidences [1].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A robust algorithm for gait cycle segmentation

Jiang

Wang

Kyrarini

et al. 2017

2017 25th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

Abstract-In this paper, a robust algorithm for gait cycle segmentation is proposed based on a peak detection approach. The proposed algorithm is less influenced by noise and outliers and is capable of segmenting gait cycles from different types of gait signals recorded using different sensor systems. The presented algorithm has enhanced ability to segment gait cycles by eliminating the false peaks and interpolating the missing peaks. The variance of segmented cycles' lengths is computed as a criterion for evaluating the performance of segmentation. The proposed algorithm is tested on gait signals of patients diagnosed with Parkinson's disease collected from three databases. The segmentation results on three types of gait signals demonstrate the capability of the proposed algorithm to segment gait cycles accurately, and have achieved better performance than the original peak detection methods.

show abstract

“…The Dynamic Time Warping (DTW) [20] is a method for finding an optimal alignment between two given time-series which may vary in speed and time. DTW-based algorithms are currently used for speech recognition [21], gesture recognition [22], robot learning [23], gait analysis [24] and for other sensorbased applications. The fundamental functionality of DTW is to define an optimal warping path (alignment) and to calculate the DTW distance (similarity) between two given time-series.…”

Section:  Automatic Selection Of Similar Demonstrationsmentioning

confidence: 99%

Robot Learning of Object Manipulation Task Actions From Human Demonstrations

Kyrarini

Haseeb²,

Ristić-Durrant³

et al. 2017

FU Mech Eng

Self Cite

View full text Add to dashboard Cite

Abstract. Robot learning from demonstration is a method which enables robots to learn in a similar way as humans. In this paper, a framework that enables robots to learn from multiple human demonstrations via kinesthetic teaching is presented. The subject of learning is a high-level sequence of actions, as well as the low-level trajectories necessary to be followed by the robot to perform the object manipulation task. The multiple human demonstrations are recorded and only the most similar demonstrations are selected for robot learning. The high-level learning module identifies the sequence of actions of the demonstrated task. Using Dynamic Time Warping (DTW) and Gaussian Mixture Model (GMM), the model of demonstrated trajectories is learned.The learned trajectory is generated by Gaussian mixture regression (GMR) from the learned Gaussian mixture model. In online working phase, the sequence of actions is identified and experimental results show that the robot performs the learned task successfully.

show abstract

Monitoring of gait performance using dynamic time warping on IMU-sensor data

Cited by 19 publications

References 11 publications

Monitoring Methods of Human Body Joints: State-of-the-Art and Research Challenges

Monitoring Methods of Human Body Joints: State-of-the-Art and Research Challenges

A robust algorithm for gait cycle segmentation

Robot Learning of Object Manipulation Task Actions From Human Demonstrations

Contact Info

Product

Resources

About