Design and evaluation of a noninvasive tongue-computer interface for individuals with severe disabilities

Kirtas, Oguzhan; Mohammadi, Mostafa; Bentsen, Bo; Veltink, Petrus H.; Struijk, Lotte N. S. Andreasen

doi:10.1109/bibe52308.2021.9635238

Cited by 5 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One-third of the disabled participants interviewed in a previous study reported that they were not interested in using the ITCI due to the need for a piercing (Caltenco et al, 2012). We presented a non-invasive approach of using the ITCI system in a pilot study (Kirtas et al, 2021), and this new method is still under development.…”

Section: Discussionmentioning

confidence: 99%

Tongue control of a five-DOF upper-limb exoskeleton rehabilitates drinking and eating for individuals with severe disabilities

Mohammadi

Knoche²,

Thøgersen³

et al. 2023

International Journal of Human-Computer Studies

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Tongue control of a five-DOF upper-limb exoskeleton rehabilitates drinking and eating for individuals with severe disabilities

Mohammadi

Knoche²,

Thøgersen³

et al. 2023

International Journal of Human-Computer Studies

View full text Add to dashboard Cite

“…Thus, it does not get affect by spinal or cord injuries. As a result, it can serve as an alternative means of Control [15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

Non-Invasive Tongue-Based HCI System Using Deep Learning for Microgesture Detection

Jasim,

Shareef

2023

RIA

View full text Add to dashboard Cite

Tongue-based Human-Computer Interaction (HCI) systems have surfaced as alternative input devices offering significant benefits to individuals with severe disabilities. However, these systems often employ invasive methods such as dental retainers, tongue piercings, and multiple mouth electrodes. These methods, due to hygiene issues and obtrusiveness, are deemed impractical for daily use. This paper presents a novel non-invasive tonguebased HCI system that utilizes deep learning for microgesture detection. The proposed system overcomes the limitations of previous methods by non-invasively detecting gestures. This is accomplished by measuring tongue vibrations via an accelerometer positioned on the Genioglossus muscle, thereby eliminating the need for in-mouth installations. The system's performance was evaluated by comparing the classification results of deep learning with four widely-used supervised machine learning algorithms, namely K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Decision Trees, and Random Forests. Raw data were preprocessed in both time and frequency domains to extract relevant patterns before classification. In addition, a deep learning Convolutional Neural Network (CNN) model was trained on the raw data, leveraging its proficiency in processing time series data and capturing intricate patterns automatically using convolutional and pooling layers. The CNN model demonstrated a 97% success rate in tongue gesture detection, indicating its high accuracy. The proposed system is also lowprofile, lightweight, and cost-effective, making it suitable for daily use in various contexts. This study thus introduces a non-invasive, efficient, and practical approach to tongue-based HCI systems.

show abstract

“…In [17], we developed a new noninvasive sensor activation method by mounting a frame with an integrated AU to the ITCI as a proof of concept for noninvasive tongue based robotic interfaces that does not require gluing or piercing an AU to the tongue. However, the current design of the ITCI with two angled positioned sensor PCBs only allows activating a portion of the sensors with a frame integrated AU.…”

Section: Introductionmentioning

confidence: 99%

Development of inductive sensors for a robotic interface based on noninvasive tongue control

Kirtas¹,

Veltink²,

Lontis³

et al. 2022

2022 International Conference on Rehabilitation Robotics (ICORR)

Self Cite

View full text Add to dashboard Cite

Tongue based robotic interfaces have shown the potential to control assistive robotic devices developed for individuals with severe disabilities due to spinal cord injury. However, current tongue-robotic interfaces require invasive methods such as piercing to attach an activation unit (AU) to the tongue. A noninvasive tongue interface concept, which used a frame integrated AU instead of a tongue attached AU, was previously proposed. However, there is a need for the development of compact one-piece sensor printed circuit boards (PCBs) to enable activation of all inductive sensors. In this study, we developed and tested four designs of compact one-piece sensor PCBs incorporating inductive sensors for the design of a noninvasive tongue-robotic interface. We measured electrical parameters of the developed sensors to detect activation and compared them with a sensor of the current version of the inductive tongue-computer interface (ITCI) by moving AUs with different contact surfaces at the surface of the sensors. Results showed that, the newly developed inductive sensors had higher and wider activation than the sensor of ITCI and the AU with a flat contact surface had 3.5 -4 times higher activation than the AU with a spherical contact surface. A higher sensor activation can result in a higher signal to noise ratio and thus a higher AU tracking resolution.

show abstract

Design and evaluation of a noninvasive tongue-computer interface for individuals with severe disabilities

Cited by 5 publications

References 26 publications

Tongue control of a five-DOF upper-limb exoskeleton rehabilitates drinking and eating for individuals with severe disabilities

Tongue control of a five-DOF upper-limb exoskeleton rehabilitates drinking and eating for individuals with severe disabilities

Non-Invasive Tongue-Based HCI System Using Deep Learning for Microgesture Detection

Development of inductive sensors for a robotic interface based on noninvasive tongue control

Contact Info

Product

Resources

About