Recognising Gait Patterns of People in Risk of Falling with a Multi-layer Perceptron

Hoffmann, Raoul; Lauterbach, C.; Techmer, A.; Conradt, Jörg; Steinhage, Axel

doi:10.1007/978-3-319-39904-1_8

Cited by 4 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first type of these floor sensors measures the impedance of electric field couplings for an array of sensor plates, which is also called near field imaging [33]. A second type measures the electric capacitance, like the ELSI ® Smart Floor by Mari Mils [34,35], or SensFloor ® by Future-Shape [3,[36][37][38][39][40][41][42][43]. The latter one was used for the data acquisition here, and is described in more detail later-on.…”

Section: Sensors For Gait and Behaviour Analysismentioning

confidence: 99%

“…It was also shown that it is possible to discern if a cat or human walks over the floor [41]. Using a multi layer perceptron with a feature extraction preprocessing step made it possible to distinguish between humans with a low or high risk of falling due to unstable gait [3] or to (roughly) estimate a walking person's age [43].…”

Section: Capacitive Floor Sensormentioning

confidence: 99%

“…This is useful when working with sensors, where patterns can be found directly in the data stream without a detour of calculating intermediate, semantically meaningful or descriptive parameters or features. In a pilot study [ 3 ] it was shown that the data generated by the sensor floor is suitable to train an artificial neural network to recognise if persons have a high risk of falling, or not. The study described here evaluated if this sensor technology is also capable of recognising very subtle changes in walking patterns.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detecting Walking Challenges in Gait Patterns Using a Capacitive Sensor Floor and Recurrent Neural Networks

Hoffmann

Brodowski

Steinhage³

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Gait patterns are a result of the complex kinematics that enable human two-legged locomotion, and they can reveal a lot about a person’s state and health. Analysing them is useful for researchers to get new insights into the course of diseases, and for physicians to track the progress after healing from injuries. When a person walks and is interfered with in any way, the resulting disturbance can show up and be found in the gait patterns. This paper describes an experimental setup for capturing gait patterns with a capacitive sensor floor, which can detect the time and position of foot contacts on the floor. With this setup, a dataset was recorded where 42 participants walked over a sensor floor in different modes, inter alia, normal pace, closed eyes, and dual-task. A recurrent neural network based on Long Short-Term Memory units was trained and evaluated for the classification task of recognising the walking mode solely from the floor sensor data. Furthermore, participants were asked to do the Unilateral Heel-Rise Test, and their gait was recorded before and after doing the test. Another neural network instance was trained to predict the number of repetitions participants were able to do on the test. As the results of the classification tasks turned out to be promising, the combination of this sensor floor and the recurrent neural network architecture seems like a good system for further investigation leading to applications in health and care.

show abstract

Section: Sensors For Gait and Behaviour Analysismentioning

confidence: 99%

Section: Capacitive Floor Sensormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Walking Challenges in Gait Patterns Using a Capacitive Sensor Floor and Recurrent Neural Networks

Hoffmann

Brodowski

Steinhage³

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…20 Hoffmann et al calculated human body positions by using fixed-size temporal windows. 21,22 Mean movement distance distribution was used as features to recognize persons with a high versus low risk of falling in [21]; trajectory localization updates were used as features to recognize the movement patterns of humans and cats in [22]. A few studies 23,24 used multiple and/or variable-size windows to represent long-term and short-term dependence between activities.…”

Section: Related Workmentioning

confidence: 99%

A multimodal fusion enabled ensemble approach for human activity recognition in smart homes

Ding

Nugent

2023

Health Informatics J

View full text Add to dashboard Cite

How to deal with multi-modality data from different types of devices is a challenging issue for accurate recognition of human activities in a smart environment. In this paper, we propose a multimodal fusion enabled ensemble approach. Firstly, useful features collected from Bluetooth beacons, binary sensors, and smart floor are extracted and presented by fuzzy logic based-method with variable-size temporal windows. Secondly, a group of support vector machine classifiers are used to perform the classification task. Finally, a weighted ensemble method is used to obtain the final prediction. Especially, by applying the geometric framework, we are able to obtain the optimal weights for the ensemble. The proposed approach is evaluated on the UJAmI dataset. The experimental results demonstrate the efficacy and robustness of the proposed method.

show abstract

Using Deep Learning to Identify Persons by their Movement on a Sensor Floor

Bader,

Liebenow,

Steinhage

2023

Proceedings of the 8th International Workshop on Sensor-Based Activity Recognition and Artificial Intelligence

View full text Add to dashboard Cite

Recognising Gait Patterns of People in Risk of Falling with a Multi-layer Perceptron

Cited by 4 publications

References 15 publications

Detecting Walking Challenges in Gait Patterns Using a Capacitive Sensor Floor and Recurrent Neural Networks

Detecting Walking Challenges in Gait Patterns Using a Capacitive Sensor Floor and Recurrent Neural Networks

A multimodal fusion enabled ensemble approach for human activity recognition in smart homes

Using Deep Learning to Identify Persons by their Movement on a Sensor Floor

Contact Info

Product

Resources

About