Machine Learning Methods for Automatic Silent Speech Recognition Using a Wearable Graphene Strain Gauge Sensor.

Silent speech recognition is the ability to recognise intended speech without audio information. Useful applications can be found in situations where sound waves are not produced or cannot be heard. Examples include speakers with physical voice impairments or environments in which audio transference is not reliable or secure. Developing a device which can detect non-auditory signals and map them to intended phonation could be used to develop a device to assist in such situations. In this work, we propose a graphene-based strain gauge sensor which can be worn on the throat and detect small muscle movements and vibrations. Machine learning algorithms then decode the non-audio signals and create a prediction on intended speech. The proposed strain gauge sensor is highly wearable, utilising graphene's unique and beneficial properties including strength, flexibility and high conductivity. A highly flexible and wearable sensor able to pick up small throat movements is fabricated by screen printing graphene onto lycra fabric. A framework for interpreting this information is proposed which explores the use of several machine learning techniques to predict intended words from the signals. A dataset of 15 unique words and four movements, each with 20 repetitions, was developed and used for the training of the machine learning algorithms. The results demonstrate the ability for such sensors to be able to predict spoken words. We produced a word accuracy rate of 55% on the word dataset and 85% on the movements dataset. This work demonstrates a proof-of-concept for the viability of combining a highly wearable graphene strain gauge and machine leaning methods to automate silent speech recognition.

Graphene foam developed with a novel two-step technique for low and high strains and pressure-sensing applications.

Freestanding, mechanically stable, and highly electrically conductive graphene foam (GF) is formed with a two-step facile, adaptable, and scalable technique. This work also demonstrates the formation of graphene foam with tunable densities and its use as strain/pressure sensor for both high and low strains and pressures.

Hydrogel mechanical properties in altered gravity.

Exposure to altered gravity influences cellular behaviour in cell cultures. Hydrogels are amongst the most common materials used to produce tissue-engineering scaffolds, and their mechanical properties play a crucial role in cell-matrix interaction. However, little is known about the influence of altered gravity on hydrogel properties. Here we study the mechanical properties of Poly (ethylene glycol) diacrylate (PEGDA) and PEGDA incorporated with graphene oxide (GO) by performing tensile tests in micro and hypergravity during a Parabolic flight campaign, and by comparing them to the same tests performed in Earth gravity. We show that gravity levels do not result in a statistically significant difference in Young's modulus.

Colossal figure of merit and compelling HER catalytic activity of holey graphyne.

Herein, we have conducted a comprehensive study to uncover the thermal transport properties and hydrogen evolution reaction catalytic activity of recently synthesized holey graphyne. Our findings disclose that holey graphyne has a direct bandgap of 1.00 eV using the HSE06 exchange-correlation functional. The absence of imaginary phonon frequencies in the phonon dispersion ensures its dynamic stability. The formation energy of holey graphyne turns out to be - 8.46 eV/atom, comparable to graphene (- 9.22 eV/atom) and h-BN (- 8.80 eV/atom). At 300 K, the Seebeck coefficient is as high as 700 µV/K at a carrier concentration of 1 × 1010 cm-2. The predicted room temperature lattice thermal conductivity (κl) of 29.3 W/mK is substantially lower than graphene (3000 W/mK) and fourfold smaller than C3N (128 W/mK). At around 335 nm thickness, the room temperature κl suppresses by 25%. The calculated p-type figure of merit (ZT) reaches a maximum of 1.50 at 300 K, higher than that of holey graphene (ZT = 1.13), γ-graphyne (ZT = 0.48), and pristine graphene (ZT = 0.55 × 10-3). It further scales up to 3.36 at 600 K. Such colossal ZT values make holey graphyne an appealing p-type thermoelectric material. Besides that, holey graphyne is a potential HER catalyst with a low overpotential of 0.20 eV, which further reduces to 0.03 eV at 2% compressive strain.

Unencapsulated and washable two-dimensional material electronic-textile for NO2 sensing in ambient air.

Materials adopted in electronic gas sensors, such as chemiresistive-based NO2 sensors, for integration in clothing fail to survive standard wash cycles due to the combined effect of aggressive chemicals in washing liquids and mechanical abrasion. Device failure can be mitigated by using encapsulation materials, which, however, reduces the sensor performance in terms of sensitivity, selectivity, and therefore utility. A highly sensitive NO2 electronic textile (e-textile) sensor was fabricated on Nylon fabric, which is resistant to standard washing cycles, by coating Graphene Oxide (GO), and GO/Molybdenum disulfide (GO/MoS2) and carrying out in situ reduction of the GO to Reduced Graphene Oxide (RGO). The GO/MoS2 e-textile was selective to NO2 and showed sensitivity to 20 ppb NO2 in dry air (0.05%/ppb) and 100 ppb NO2 in humid air (60% RH) with a limit of detection (LOD) of ~ 7.3 ppb. The selectivity and low LOD is achieved with the sensor operating at ambient temperatures (~ 20 °C). The sensor maintained its functionality after undergoing 100 cycles of standardised washing with no encapsulation. The relationship between temperature, humidity and sensor response was investigated. The e-textile sensor was embedded with a microcontroller system, enabling wireless transmission of the measurement data to a mobile phone. These results show the potential for integrating air quality sensors on washable clothing for high spatial resolution (< 25 cm2)-on-body personal exposure monitoring.

Covalently interconnected transition metal dichalcogenide networks via defect engineering for high-performance electronic devices.

Solution-processed semiconducting transition metal dichalcogenides are at the centre of an ever-increasing research effort in printed (opto)electronics. However, device performance is limited by structural defects resulting from the exfoliation process and poor inter-flake electronic connectivity. Here, we report a new molecular strategy to boost the electrical performance of transition metal dichalcogenide-based devices via the use of dithiolated conjugated molecules, to simultaneously heal sulfur vacancies in solution-processed transition metal disulfides and covalently bridge adjacent flakes, thereby promoting percolation pathways for the charge transport. We achieve a reproducible increase by one order of magnitude in field-effect mobility (µFE), current ratio (ION/IOFF) and switching time (τS) for liquid-gated transistors, reaching 10-2 cm2 V-1 s-1, 104 and 18 ms, respectively. Our functionalization strategy is a universal route to simultaneously enhance the electronic connectivity in transition metal disulfide networks and tailor on demand their physicochemical properties according to the envisioned applications.

Novel graphene foam composite with adjustable sensitivity for sensor applications.

In this study, free-standing graphene foam (GF) was developed by a three-step method: (1) vacuum-assisted dip-coating of nickel foam (Ni-F) with graphene oxide (GO), (2) reduction of GO to reduced graphene oxide (rGO), and then (3) etching out the nickel scaffold. Pure GF samples were tested for their morphology, chemistry, and mechanical integrity. GF mimics the microstructure of Ni-F while individual bones of GF were hollow, because of the complete removal of nickel. The GF-PDMS composites were tested for their ability to sense both compressive and bending strains in the form of change in electrical resistance. The composite showed different sensitivity to bending and compression. Upon applying a 30% compressive strain on the GF-PDMS composite, its resistance increased to ∼120% of its original value. Similarly, bending a sample to a radius of 1 mm caused the composite to change its resistance to ∼52% of its original resistance value. The relative change in resistance of the composite by an applied pressure/strain can be tuned to considerably different values by heat-treating the GF at different temperatures prior to infusing PDMS into its scaffold. Upon heat treating the GF at 800 °C prior to PDMS infusion, the GF-PDMS demonstrated ∼10 times better sensitivity than the untreated sample for a compressive strain of 20%. The composite was also tested for its ability to retain a change in electrical resistance when a brief load/strain is applied. The GF-PDMS composite was tested for at least 500 cycles under compressive cyclic loading and showed good electromechanical durability. Finally, it was demonstrated that the composite can be used to measure human blood pressure when attached to human skin.

Highly electrically conductive nanocomposites based on polymer-infused graphene sponges.

Conductive polymer composites require a three-dimensional 3D network to impart electrical conductivity. A general method that is applicable to most polymers for achieving a desirable graphene 3D network is still a challenge. We have developed a facile technique to fabricate highly electrical conductive composite using vacuum-assisted infusion of epoxy into graphene sponge GS scaffold. Macroscopic GSs were synthesized from graphene oxide solution by a hydrothermal method combined with freeze drying. The GS/epoxy composites prepared display consistent isotropic electrical conductivity around 1 S/m, and it is found to be close to that of the pristine GS. Compared with neat epoxy, GS/epoxy has a 12-orders-of-magnitude increase in electrical conductivity, attributed to the compactly interconnected graphene network constructed in the polymer matrix. This method can be extended to other materials to fabricate highly conductive composites for practical applications such as electronic devices, sensors, actuators, and electromagnetic shielding.