Temporal Pattern Recognition in Gait Activities Recorded With a Footprint Imaging Sensor System

Costilla-Reyes, Omar; Scully, Patricia; Ozanyan, Krikor B.

doi:10.1109/jsen.2016.2583260

Cited by 39 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With frame rates of 256 Hz and spatial sampling adequate for inverting the data into footstep image frames, it was possible to capture in substantial detail the dynamics of an uninterrupted sequence of at least 4 footfalls at a time. Costilla-Reyes et al [97] demonstrated that, in the classification of 10 manners of walking from temporal data subsets, deep learning models (Deep Feed Forward ANN with 10 hidden layers and a RNN) outperformed shallow learning, with some exceptions attributed to the shortage of training data. This was partially mitigated in a further work [98] where the UoM-Gat-13 dataset was introduced, as a full set of spatiotemporal raw signals (1400 frames at 256 Hz from each of the 116 sensors) from 10 manners of walking and 3 dual tasks.…”

Section: Floor Sensorsmentioning

confidence: 99%

Deep Learning for Monitoring of Human Gait: A Review

2019

Self Cite

View full text Add to dashboard Cite

The essential human gait parameters are briefly reviewed, followed by a detailed review of the state of the art in deep learning for the human gait analysis. The modalities for capturing the gait data are grouped according to the sensing technology: video sequences, wearable sensors, and floor sensors, as well as the publicly available datasets. The established artificial neural network architectures for deep learning are reviewed for each group, and their performance are compared with particular emphasis on the spatiotemporal character of gait data and the motivation for multi-sensor, multi-modality fusion. It is shown that by most of the essential metrics, deep learning convolutional neural networks typically outperform shallow learning models. In the light of the discussed character of gait data, this is attributed to the possibility to extract the gait features automatically in deep learning as opposed to the shallow learning from the handcrafted gait features.

show abstract

Section: Floor Sensorsmentioning

confidence: 99%

Deep Learning for Monitoring of Human Gait: A Review

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since the POF sensor conforms mechanically to the substrate on which it is placed, the sensor signal depends on the mechanical properties of the substrate, supporting the sensor layer. For human gait monitoring the typical substrate is a commercially available carpet underlay placed on a non-deformable surface; however, the technology is in principle scalable to map weights outside the typical range for humans, as previously demonstrated by weighing lowermass household objects [3].…”

Section: Sensing Methodologymentioning

confidence: 99%

Floor sensors of animal weight and gait for precision livestock farming

et al. 2017

View full text Add to dashboard Cite

Abstract-We report first results on developing smart sensor systems for the automatic and frequent collection of animal weight and gait data, under the hostile conditions of a livestock farm. The novelty in our approach is to sense frequently the animals' floor contact, in suitably chosen locations, under natural and unobtrusive conditions. We demonstrate a pilot low profile rubberized mat sensor heads, delivering a large number of plastic optical fiber transmission measurements taken frequently from individual deformation sensors. The acquired data allows gait analysis from guided-path tomography images or by machine learning. We demonstrate weight estimation with accuracy better than 1% over a range suitable for deployment in pig farms.

show abstract

“…Scully et al developed a range of signal processing methods to extract data from POF sensor elements to measure human motion ranging from balance to walking [18,64]. Together with tomographic and analogue null balance methods, they explored pattern recognition and machine learning classification, to identify different types of walking.…”

Section: Intensity Based Optical Fiber Sensorsmentioning

confidence: 99%

“…There is a myriad of applications where POF technology is used such as geophysical surveying and security [14,15], groundwater level monitoring [16], water detection in fuel [17], healthcare [18], optoacoustic endoscopic imaging [19], central arterial pressure monitoring [20], on-line remote dosimetry [21], structural health monitoring [22], decubitus prevention [23], among others. As we can observe, all these applications are closely related to human safety.…”

Section: Introductionmentioning

confidence: 99%

Polymer optical fiber sensors in human life safety

Marques

Webb

Andre

2017

Optical Fiber Technology

104

View full text Add to dashboard Cite

The current state of research into polymer optical fiber (POF) sensors linked to safety in human life is summarized in this paper. This topic is directly related with new solutions for civil aircraft, structural health monitoring, healthcare and biomedicine fields. In the last years, the properties of polymers have been explored to identify situations offering potential advantages over conventional silica fiber sensing technology, replacing, in some cases, problematic electronic technology used in these mentioned fields, where there are some issues to overcome. POFs could preferably replace their silica counterparts, with improved performance and biocompatibility. Finally, new developments are reported which use the unique properties of POF.

show abstract

Temporal Pattern Recognition in Gait Activities Recorded With a Footprint Imaging Sensor System

Cited by 39 publications

References 17 publications

Deep Learning for Monitoring of Human Gait: A Review

Deep Learning for Monitoring of Human Gait: A Review

Floor sensors of animal weight and gait for precision livestock farming

Polymer optical fiber sensors in human life safety

Contact Info

Product

Resources

About