Preliminary Investigation of Textile-Based Strain Sensors for the Detection of Human Gait Phases Using Machine Learning

Rezaei, Ahmad Asgharian; Ejupi, Andreas; Gholami, Mohsen; Ferrone, Andrea; Menon, Carlo

doi:10.1109/biorob.2018.8487880

Cited by 17 publications

(25 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Random forest is an ensemble of decision trees that has shown promising results when compared with conventional machine learning algorithms including support vector machine and neural networks in regression and classification applications for strain sensor’s data analysis [ 39 , 47 ]. Random forest models are robust to outliers, nonlinear and unbalanced data, and produce low bias and moderate variance [ 48 , 49 ].…”

Section: Methodsmentioning

confidence: 99%

Fatigue Monitoring in Running Using Flexible Textile Wearable Sensors

Gholami

Napier

Patiño

et al. 2020

Sensors

View full text Add to dashboard Cite

Fatigue is a multifunctional and complex phenomenon that affects how individuals perform an activity. Fatigue during running causes changes in normal gait parameters and increases the risk of injury. To address this problem, wearable sensors have been proposed as an unobtrusive and portable system to measure changes in human movement as a result of fatigue. Recently, a category of wearable devices that has gained attention is flexible textile strain sensors because of their ability to be woven into garments to measure kinematics. This study uses flexible textile strain sensors to continuously monitor the kinematics during running and uses a machine learning approach to estimate the level of fatigue during running. Five female participants used the sensor-instrumented garment while running to a state of fatigue. In addition to the kinematic data from the flexible textile strain sensors, the perceived level of exertion was monitored for each participant as an indication of their actual fatigue level. A stacked random forest machine learning model was used to estimate the perceived exertion levels from the kinematic data. The machine learning algorithm obtained a root mean squared value of 0.06 and a coefficient of determination of 0.96 in participant-specific scenarios. This study highlights the potential of flexible textile strain sensors to objectively estimate the level of fatigue during running by detecting slight perturbations in lower extremity kinematics. Future iterations of this technology may lead to real-time biofeedback applications that could reduce the risk of running-related overuse injuries.

show abstract

Section: Methodsmentioning

confidence: 99%

Fatigue Monitoring in Running Using Flexible Textile Wearable Sensors

Gholami

Napier

Patiño

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…are installed on rigid and specific sized objects. To move forward in the area of etextiles, these electronic parts are being integrated on a textile substrate including wearable clothing to make wearable electronic structures [1][2][3][4][5][6][7][8]. Integration of electronics and cooperation of this industry with the textile industry to produce e-textile products based on specific user requirements is supposed to be booming in the near future this industry [9].…”

Section: Introductionmentioning

confidence: 99%

“…It is important to know how to use existing industrial processes, or to develop new ones that are able to scale up production, ensuring the behavior and performance of prototypes. Despite the technical challenges, there are already some examples of wearable e-textiles where sensors, actuators, and production techniques were used to seamlessly embed electronic features into traditional wearable textiles, which allow for daily use without a bionic stigma [3][4][5][6][7][12][13][14]. E-textile systems can be used for detection of numerous signals from their environment (personal and external) and for sending data remotely to databases (clouds), besides, to responding to the specific stimuli [12,15,16].…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, usage of value-added textiles is getting attractions in different fields including medical, sports, detection or monitoring of movement, etc. with the help of actuators and sensors installed within wearable textiles [4][5][6]17]. This dynamic industry is gaining customers interests due to innovations in this area.…”

Section: Introductionmentioning

confidence: 99%

“…Next level of achievement is based on adding the sensors, actuators, antennas, and conductor or semiconductor fibers on wearable textile surfaces and to get the wearable motherboard specially designed targeting the end usage [19][20][21][22]. There are various ongoing researches, which develop very comfortable e-textiles for specific end-users such as pilots, astronauts, disabled people by implementing highly stretchable, flexible and soft wearable sensors [4,6,[23][24][25][26][27].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Protocol to assess the quality of transmission lines within smart textile structures

et al. 2020

View full text Add to dashboard Cite

a b s t r a c tThe washability issue is always a challenge for electronic textiles in terms of application. It reduces their reliability, makes them not robust enough, and therefore not ready for the market. In this study, a novel protocol was designed to test the performance of conductive threads under wet situation in order to simulate the washing cycle. In this content, two commercially available silver-plated polyamide threads having the same thread count were used and washing results of each thread were discussed. Transmission lines with silver-plated polyamide threads onto cotton woven fabric were produced via sewing (single-line stitch) and embroidery techniques (three-line stitch) to improve the conductivity and robustness. For the simulation of the wash process, Martindale abrasion tester was used under wet and dry conditions. Moreover, felts of abrasion tester and transmission lines were put into different solutions, i.e., water, water with standardized detergent and water with commercially available detergent. After wetting specimens, abrasion tests were performed on transmission lines, and linear electrical resistance measurements were recorded with the multi meter before abrasion and every 1500 cycles up to 4500 cycles in wet conditions and also after drying the transmission lines. Finally, abrasion impact on silver-plated polyamide threads was investigated by optical microscope. It has been found that silver coating on the conductive thread was damaged when subjected to abrasion cycles, especially in wet states. Water itself has stress impact on samples provoking the electrical resistance increase rapidly. Commercial detergent with water was found to have the most damaging effect on the conductive threads because of extra particles presence to enhance the washing performance. In terms of integration methods, better electrical conductivity values were achieved in three-line embroidery transmission lines due to multiple interconnection points in the embroidery network.

show abstract