Hand Gesture Recognition With Acoustic Myography and Wavelet Scattering Transform

Al-Timemy, Ali H.; Serrestou, Youssef; Khushaba, Rami N.; Yacoub, Slim; Raoof, Kosai

doi:10.1109/access.2022.3212146

Cited by 10 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This may be imputed to the non-parametric nature of KNN [37], which does not require a priori knowledge of the data distribution and it can fit irregular decision functions due to an increase of complex patterns present in the data. Conversely, both the LDA and linear SVM-based architectures may suffer in fine partitioning the feature space required in this study and are not encountered in typical hand gesture recognition problems where both linear SVM and LDA resulted to be efficient [25,44]. Hence, rather than employ linear approaches, the results suggest the use of nonlinear kernels to better capture the complex hidden pattern within the data.…”

Section: Discussionmentioning

confidence: 91%

Intelligent Human–Computer Interaction: Combined Wrist and Forearm Myoelectric Signals for Handwriting Recognition

Tigrini,

Ranaldi,

Verdini

et al. 2024

Bioengineering

View full text Add to dashboard Cite

Recent studies have highlighted the possibility of using surface electromyographic (EMG) signals to develop human–computer interfaces that are also able to recognize complex motor tasks involving the hand as the handwriting of digits. However, the automatic recognition of words from EMG information has not yet been studied. The aim of this study is to investigate the feasibility of using combined forearm and wrist EMG probes for solving the handwriting recognition problem of 30 words with consolidated machine-learning techniques and aggregating state-of-the-art features extracted in the time and frequency domains. Six healthy subjects, three females and three males aged between 25 and 40 years, were recruited for the study. Two tests in pattern recognition were conducted to assess the possibility of classifying fine hand movements through EMG signals. The first test was designed to assess the feasibility of using consolidated myoelectric control technology with shallow machine-learning methods in the field of handwriting detection. The second test was implemented to assess if specific feature extraction schemes can guarantee high performances with limited complexity of the processing pipeline. Among support vector machine, linear discriminant analysis, and K-nearest neighbours (KNN), the last one showed the best classification performances in the 30-word classification problem, with a mean accuracy of 95% and 85% when using all the features and a specific feature set known as TDAR, respectively. The obtained results confirmed the validity of using combined wrist and forearm EMG data for intelligent handwriting recognition through pattern recognition approaches in real scenarios.

show abstract

Section: Discussionmentioning

confidence: 91%

Intelligent Human–Computer Interaction: Combined Wrist and Forearm Myoelectric Signals for Handwriting Recognition

Tigrini,

Ranaldi,

Verdini

et al. 2024

Bioengineering

View full text Add to dashboard Cite

show abstract

“…A sliding average filter was initially applied to the raw FMG signal samples to mitigate noise arising from instruments and the environment. As recommended in [12], [35], a window length of 200 ms and a moving step size of 50 ms were employed for sliding filtering, aligning with the suggested range of 150-250 ms. Given the relatively concentrated values and to neutralize the impact of individual sample data, the filtered data underwent normalization using the min-max normalization method.…”

Section: Gesture Set and Experimental Designmentioning

confidence: 99%

Channel Selection for Gesture Recognition Using Force Myography: A Universal Model for Gesture Measurement Points

Xiao,

Du,

Yan

et al. 2024

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Gesture recognition has emerged as a significant research domain in computer vision and humancomputer interaction. One of the key challenges in gesture recognition is how to select the most useful channels that can effectively represent gesture movements. In this study, we have developed a channel selection algorithm that determines the number and placement of sensors that are critical to gesture classification. To validate this algorithm, we constructed a Force Myography (FMG)-based signal acquisition system. The algorithm considers each sensor as a distinct channel, with the most effective channel combinations and recognition accuracy determined through assessing the correlation between each channel and the target gesture, as well as the redundant correlation between different channels. The database was created by collecting experimental data from 10 healthy individuals who wore 16 sensors to perform 13 unique hand gestures. The results indicate that the average number of channels across the 10 participants was 3, corresponding to an 75% decrease in the initial channel count, with an average recognition accuracy of 94.46%. This outperforms four widely adopted feature selection algorithms, including Relief-F, mRMR, CFS, and ILFS. Moreover, we have established a universal model for the position of gesture measurement points and verified it with an additional five participants, resulting in an average recognition accuracy of 96.3%. This study provides a sound

show abstract

“…A wide range of microphones are extensively applied for capturing biological signals of hemodynamics, respiratory mechanics, and joint movement [15]. Phonomyography (PMG), also known as acoustic myography or muscle sound, is a technique that uses a microphone to detect low frequency acoustic waves triggered by muscle fiber movement [16][17][18]. Previous studies have already proved the feasibility of this technique for intraoperative neuromuscular monitoring [19,20].…”

Section: Introductionmentioning

confidence: 99%

The Effect of Phonomyography Prototype for Intraoperative Neuromuscular Monitoring: A Preliminary Study

Dong,

Guo,

Yang

et al. 2024

Bioengineering

View full text Add to dashboard Cite

Quantitative neuromuscular monitoring, as extolled by clinical guidelines, is advocated to circumvent the complications associated with neuromuscular blockers (NMBs), such as residual neuromuscular block (rNMB). Nonetheless, the worldwide utilization of such methods remains undesirable. Phonomyography (PMG) boasts the advantages of convenience, stability, and multi-muscle recording which may be a promising monitoring method. The purpose of this preliminary study is conducting a feasibility analysis and an effectiveness evaluation of a PMG prototype under general anesthesia. A prospective observational preliminary study was conducted. Twenty-five adults who had undergone none-cardiac elective surgery were enrolled. The PMG prototype and TOF-Watch SX simultaneously recorded the pharmacodynamic properties of single bolus rocuronium at the ipsilateral adductor pollicis for each patient. For the primary outcome, the time duration to 0.9 TOF ratio of the two devices reached no statistical significance (p > 0.05). For secondary outcomes, the multi-temporal neuromuscular-monitoring measurements between the two devices also reached no statistical significance (p > 0.05). What is more, both the Spearman’s and Pearson’s correlation tests revealed a strong correlation across all monitoring periods between the PMG prototype and TOF-Watch SX. Additionally, Bland–Altman plots demonstrated a good agreement between the two devices. Thus, the PMG prototype was a feasible, secure, and effective neuromuscular-monitoring technique during general anesthesia and was interchangeable with TOF-Watch SX.

show abstract

Hand Gesture Recognition With Acoustic Myography and Wavelet Scattering Transform

Cited by 10 publications

References 44 publications

Intelligent Human–Computer Interaction: Combined Wrist and Forearm Myoelectric Signals for Handwriting Recognition

Intelligent Human–Computer Interaction: Combined Wrist and Forearm Myoelectric Signals for Handwriting Recognition

Channel Selection for Gesture Recognition Using Force Myography: A Universal Model for Gesture Measurement Points

The Effect of Phonomyography Prototype for Intraoperative Neuromuscular Monitoring: A Preliminary Study

Contact Info

Product

Resources

About