High Dimensional Computing Gesture Recognition

Обзор

The primary objective of this study is the Improvement of gesture recognition and classification accuracy through the use of the HDC algorithm compared to other classification methods (KNN, RF, SGD, NC). The recognition rate will be expressed by the sensitivity and specificity of gesture recognition. The model will be trained on a portion of the dataset and tested on the remaining part to avoid any bias. The secondaries objectives are the : * Improvement of gesture recognition accuracy with our HDC algorithm compared to other standard models. * Calculation of gesture recognition rates depending on the number of electrodes used and their position. * Subject's assessment of device comfort rated above 6 on a 10-level visual analog scale. * Subject's assessment of ease of performing the gesture rated above 6 on a 10-level visual analog scale.

Подробное описание

This project aims to work on gesture recognition based on surface electromyography (EMG) recorded on the forearm. The CEA is currently developing a learning algorithm based on hyperdimensional computing designed to improve the accuracy and latency of gesture recognition. Unlike conventional computing methods, the developed approach relies on (pseudo) random hypervectors. This brings significant advantages: a simple algorithm with a well-defined set of arithmetic operations, extremely robust to noise and errors, with fast, one-pass learning that could ultimately benefit from a memory-centric architecture with a high degree of parallelism.

This research could lead to multiple applications, such as video gaming or the metaverse, but also strongly interests the healthcare field, for example in robotic prostheses, tele-surgery applications, or simply medical training using virtual reality applications.

Вмешательства

• Устройство HDC-GCog
  Surface electromyography records

Первичные конечные точки

• Gesture recognition rate using a device composed of 32 high-frequency surface EMG electrodes [Срок оценки: 3 hours]

Вторичные конечные точки (3)

• Real-time gesture recognition (latency <100ms) [Срок оценки: 3 hours]
• Validation of the positioning and number of electrodes used for EMG acquisition in order to maximize gesture recognition rates [Срок оценки: 3 hours]
• Analysis of the subject's feedback regarding the ease of performing the gestures (in the form of a questionnaire) [Срок оценки: 3 hours]

Критерии участия

Критерии включения

• Healthy, right-handed volunteer subject,
• Male or female,
• Age between 18 and 65 years inclusive,
• BMI < 30 kg/m²,
• Minimum forearm circumference less than 15 cm,
• Subjects agree to shaving or trimming of the right forearm.
• Agreement to the study non-opposition form,
• Subject affiliated with a social security scheme,
• Registered in the national database of individuals who participate in biomedical research

Критерии исключения

• Subject with a known motor problem in the right forearm and hand,
• Known allergy or intolerance to one of the electrode components,
• Presence of a lesion in the measurement area,
• Subject with an active medical implant (e.g. pacemaker, cochlear implant, etc.),
• Subject wearing a contraceptive implant in the measurement area.
• Female subject aware of pregnancy at the time of measurement,
• Subject refusing to shave or trim the area or whose body hair precludes shaving or trimming the area,
• Presence of a pathology likely to alter the EMG.
• Persons referred to in Articles L1121-5 to L1121-8 of the Public Health Code (corresponds to all protected persons: pregnant women, women in labour, breastfeeding mothers, persons deprived of their liberty by judicial or administrative decision, persons receiving psychiatric care under Articles L. 3212-1 and L. 3213-1 who do not fall under the provisions of Article L. 1121-8, persons admitted to a health or social establishment for purposes other than research, minors, persons subject to a legal protection measure or unable to express their consent).

Критерии приведены из реестра в оригинале (на английском). Окончательную оценку соответствия проводит исследовательский центр.

Здоровые добровольцы: Да

Дизайн исследования

Распределение

Не применимо

Модель

Одна группа

Маскирование

Открытое

Основная цель

Другое

Центры проведения

Франция · 1 центр

• Clinatec Cea/Chuga — Grenoble

Публикации

• Salerno, A., Barraud, S. (2024). Evaluation and implementation of High-Dimensionnal Computing for gesture recognition using sEMG signals. Proceedings of the 2024 International Conference on Control, Automation and Diagnosis (ICCAD)
• Salerno, A., Barraud, S. (2025). Novel and efficient hyperdimensional encoding of surface electromyography signals for hand gesture recognition, Biosensor 2025.
• A. Sultana, F. Ahmed, Md. S. Alam, A systematic review on surface electromyography-based classification system for identifying hand and finger movements, Healthcare Analytics, 3, 100126, 2022, DOI:10.1016/j.health.2022.100126
• Sgambato, B. G., Castellano, G. (2022). Performance comparison of different classifiers applied to gesture recognition from sEMG signals. In Bastos-Filho, T. F., de Oliveira Caldeira, E. M., Frizera-Neto, A. (Eds.), XXVII Brazilian Congress on Biomedical Engineering. CBEB 2020. IFMBE Proceedings, Vol. 83. Springer, Cham

Идентификаторы

NCT: NCT07155460 · 38RC25.0179

Первоисточники (государственные реестры)

• ClinicalTrials.gov (NIH, США)

Открыть это исследование на ClinicalTrials.gov ↗