Complex conductivity reconstruction in multiple frequency electrical impedance tomography for fabric-based pressure sensor

Yang, Chuanlei; Mohammed, Ameer; Mohamadou, Youssoufa; Oh, Tong In; Soleimani, Masoud

doi:10.1108/sr-03-2014-626

Cited by 17 publications

(10 citation statements)

References 11 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pressure sensor was made using Veloster material which acts as a semi-permeable layer between two pieces of conductive fabric to create pressure on it (Yang et al, 2015). After experimentation, it was observed that the response to pressure was not steady using Veloster (Randhawa et al, 2018).…”

Section: Hardware Descriptionmentioning

confidence: 99%

Human activity detection using machine learning methods from wearable sensors

Randhawa

Shanthagiri

Kumar

et al. 2020

View full text Add to dashboard Cite

Purpose The paper aims to develop a novel method for the classification of different physical activities of a human being, using fabric sensors. This method focuses mainly on classifying the physical activity between normal action and violent attack on a victim and verifies its validity. Design/methodology/approach The system is realized as a protective jacket that can be worn by the subject. Stretch sensors, pressure sensors and a 9 degree of freedom accelerometer are strategically woven on the jacket. The jacket has an internal bus system made of conductive fabric that connects the sensors to the Flora chip, which acts as the data acquisition unit for the data generated. Different activities such as still, standing up, walking, twist-jump-turn, dancing and violent action are performed. The jacket in this study is worn by a healthy subject. The main phases which describe the activity recognition method undertaken in this study are the placement of sensors, pre-processing of data and deploying machine learning models for classification. Findings The effectiveness of the method was validated in a controlled environment. Certain challenges are also faced in building the experimental setup for the collection of data from the hardware. The most tedious challenge is to collect the data without noise and error, created by voltage fluctuations when stretched. The results show that the support vector machine classifier can classify different activities and is able to differentiate normal action and violent attacks with an accuracy of 98.8%, which is superior to other methods and algorithms. Practical implications This study leads to an understanding of human physical movement under violent activity. The results show that data compared with normal physical motion, which includes even a form of dance is quite different from the data collected during violent physical motion. This jacket construction with woven sensors can capture every dimension of the physical motion adding features to the data on which the machine learning model will be built. Originality/value Unlike other studies, where sensors are placed on isolated parts of the body, in this study, the fabric sensors are woven into the fabric itself to collect the data and to achieve maximum accuracy instead of using isolated wearable sensors. This method, together with a fabric pressure and stretch sensors, can provide key data and accurate feedback information when the victim is being attacked or is in a normal state of action.

show abstract

Section: Hardware Descriptionmentioning

confidence: 99%

Human activity detection using machine learning methods from wearable sensors

Randhawa

Shanthagiri

Kumar

et al. 2020

View full text Add to dashboard Cite

show abstract

“…where α is the regularization parameter, and I is the identity matrix. 23 Here, the sensitivity method was adopted to compute J. 24 Each term of J (i.e., Jlkn), which is the derivative of the measured boundary voltage with respect to the conductivity of each finite element voxel, is evaluated using (5):…”

Section: B Inverse Problemmentioning

confidence: 99%

“…where α is the regularization parameter, and I is the identity matrix. 23 Here, the sensitivity method was adopted to compute J . 24 Each term of J (i.e.…”

Section: Eit Backgroundmentioning

confidence: 99%

Graphene sensing meshes for densely distributed strain field monitoring

Gupta

Vella

et al. 2019

Structural Health Monitoring

View full text Add to dashboard Cite

The objective of this study is to design and validate distributed strain field monitoring using a patterned nanocomposite “sensing mesh” that is coupled with an electrical impedance tomography (EIT) measurement strategy and algorithm. Although EIT has been used in other studies and in conjunction with a piezoresistive thin film for spatial damage detection, different strain components cannot be directly extracted from reconstructed EIT conductivity maps. Therefore, this study seeks to address this issue by patterning piezoresistive graphene-based thin films to form a mesh-like pattern. The high aspect ratio of each nanocomposite grid interconnect acts as a linear distributed strain sensor, capable of resolving strains along the entire length and direction of the element. This study first began with the design, fabrication, and characterization of the strain sensing response of a graphene-based thin film of high strain sensitivity. Second, the strain-sensitive film was spray-coated onto patterned polymer substrates to form the sensing meshes, which were then subjected to load tests. Upon validating distributed strain field monitoring through EIT, its applicability for field implementation and damage characterization was also demonstrated by instrumenting sensing meshes in the column of a seven-story reinforced-concrete building subjected to shaking table earthquake excitations. The large-scale shaking table test results successfully validated distributed damage detection.

show abstract

“…Stretchable conductive materials incorporated with electrical impedance tomography (EIT) can be an alternative solution to overcome aforementioned limitations4243444546474849505152. Electrical impedance tomography is a technique that computes internal conductivity distribution from continuum conductive model using electrodes fabricated along the boundary of the conductive material53.…”

mentioning

confidence: 99%

“…Here, the electrodes are used to apply electrical currents and to measure electrical potentials. This technique has been used to demonstrate a stretchable and sensitive electronic skin covering on three dimensional contoured surfaces without any internal wiring using conductive fabric4344505152, conductive rubber464748, and conductive liquid45. In these literatures, no complex array of stretchable electrodes needs to be fabricated within the entire sensing area.…”

mentioning

confidence: 99%

Soft Nanocomposite Based Multi-point, Multi-directional Strain Mapping Sensor Using Anisotropic Electrical Impedance Tomography

Lee

Kwon

Cho

et al. 2017

Sci Rep

View full text Add to dashboard Cite

The practical utilization of soft nanocomposites as a strain mapping sensor in tactile sensors and artificial skins requires robustness for various contact conditions as well as low-cost fabrication process for large three dimensional surfaces. In this work, we propose a multi-point and multi-directional strain mapping sensor based on multiwall carbon nanotube (MWCNT)-silicone elastomer nanocomposites and anisotropic electrical impedance tomography (aEIT). Based on the anisotropic resistivity of the sensor, aEIT technique can reconstruct anisotropic resistivity distributions using electrodes around the sensor boundary. This strain mapping sensor successfully estimated stretch displacements (error of 0.54 ± 0.53 mm), surface normal forces (error of 0.61 ± 0.62 N), and multi-point contact locations (error of 1.88 ± 0.95 mm in 30 mm × 30 mm area for a planar shaped sensor and error of 4.80 ± 3.05 mm in 40 mm × 110 mm area for a three dimensional contoured sensor). In addition, the direction of lateral stretch was also identified by reconstructing anisotropic distributions of electrical resistivity. Finally, a soft human-machine interface device was demonstrated as a practical application of the developed sensor.

show abstract

Complex conductivity reconstruction in multiple frequency electrical impedance tomography for fabric-based pressure sensor

Cited by 17 publications

References 11 publications

Human activity detection using machine learning methods from wearable sensors

Human activity detection using machine learning methods from wearable sensors

Graphene sensing meshes for densely distributed strain field monitoring

Soft Nanocomposite Based Multi-point, Multi-directional Strain Mapping Sensor Using Anisotropic Electrical Impedance Tomography

Contact Info

Product

Resources

About