In this article, we propose a novel neuromuscular password-based user authentication method. The method consists of two parts: surface electromyogram (sEMG) based finger muscle isometric contraction ...password (FMICP) and neuromuscular biometrics. FMICP can be entered through isometric contraction of different finger muscles in a prescribed order without actual finger movement, which makes it difficult for observers to obtain the password. In our study, the isometric contraction patterns of different finger muscles were recognized through high-density sEMG signals acquired from the right dorsal hand. Moreover, both time-frequency-space domain features at macroscopic level (interference-pattern EMG) and motor neuron firing rate features at microscopic level (via decomposition) were extracted to represent neuromuscular biometrics, serving as a second defense. The FMICP and macro-micro neuromuscular biometrics together form a neuromuscular password. The proposed neuromuscular password achieved an equal error rate (EER) of 0.0128 when impostors entered a wrong FMICP. Even when impostors entered the correct FMICP, the neuromuscular biometrics, as the second defense, inhibited impostors with an EER of 0.1496. To the best of our knowledge, this is the first study to use individually unique neuromuscular information during unobservable muscle isometric contractions for user authentication, with training and testing data acquired on different days.
Measuring the physical, physiological, behavioral, or chemical characteristics of an individual as biometrics for personal identification has attracted increasing attention in smart environment ...applications. Noncancelability and cross-application invariance are two flaws of traditional DNA, face, and fingerprint-based biometrics because users cannot volitionally change the biometric template. In this work, we acquired high-density surface electromyogram (HD-sEMG) signals encoded by gesture passwords as biometrics. The different sEMG patterns under different motor tasks allow users to enroll multiple accounts using sEMG under different hand gestures as biometrics. By simply changing to a new gesture password, users can cancel the original template once it is compromised. Even if impostors enter the correct gesture password, the individual differences of HD-sEMG as the second defense can still achieve excellent performance. To improve the current state-of-the-art identification accuracy, we acquired 256-channel forearm HD-sEMG and decoded high-resolution neuromuscular information in temporal-spectral-spatial domain. We achieved a high identification accuracy of 99.85% on a 200-account (20 subjects <inline-formula> <tex-math notation="LaTeX">\times10 </tex-math></inline-formula> accounts per subject) recognition task, with training and testing data acquired 3 to 25 days apart. Moreover, to address the concern of "unknown identities," we applied an "authentication + identification" validation, achieving high accuracy of 93.81% on a 200-account (16 enrolled subjects +4 unknown subjects) <inline-formula> <tex-math notation="LaTeX">\times10 </tex-math></inline-formula> accounts per subject task. Our work substantially improves the current state-of-the-art accuracy for cross-day sEMG biometric identification (improved from <inline-formula> <tex-math notation="LaTeX">\sim 88 </tex-math></inline-formula>% to >99% with a similar number of identified classes).
The progression of prosthetic technology, enabling precise thumb control and movement, has reached a stage where noninvasive techniques for capturing bioelectrical signals from muscle activity are ...preferred over alternative methods. While electromyography's applications extend beyond just interfacing with prostheses, this initial investigation delves into evaluating various classifiers' accuracy in identifying rest and contraction states of the thumb muscles using extrinsic forearm readings. Employing a High-Density Surface Electromyogram (HD-sEMG) device, bioelectrical signals generated by muscle activity, detectable from the skin's surface, were transformed into contours. A training system for the thumb induced muscle activity in four postures: 0°, 30°, 60°, and 90°. The collection of HD-sEMG signals originating from both the anterior and posterior forearms of seventeen participants has been proficiently classified using a neural network with 100% accuracy and a mean square error (MSE) of 1.4923 x 10-5 based on the testing dataset. This accomplishment in classification was realized by employing the Bayesian regularization backpropagation (trainbr) training technique, integrating seven concealed layers, and adopting a training-validation-testing proportion of 70-15-15. In the realm of future research, an avenue worth exploring involves the potential integration of real-time feedback mechanisms predicated on the recognition of thumb muscle contraction states. This integration could offer an enhanced interaction experience between users and prosthetic devices. ABSTRAK: Perkembangan teknologi prostetik mengguna pakai kaedah selamat iaitu isyarat bioelektrikal yang diperoleh dari pergerakan otot lebih digemari digunakan berbanding kaedah alternatif. Ini membolehkan kawalan dan pergerakan ibu jari dengan tepat. Sementara aplikasi elektromiografi telah melangkah jauh melebihi antara muka prostesis. Kajian awal ini mengkaji pelbagai ketepatan klasifikasi dalam mengenal pasti keadaan rehat dan kontraksi otot ibu jari menggunakan bacaan lengan bawah ekstrinsik. Dengan menggunakan peranti Elektromiogram Permukaan Kepadatan-Tinggi (HD-sEMG), isyarat bioelektrikal yang terhasil dari pergerakan otot, boleh ditanggalkan dari permukaan kulit, di ubah kepada kontur. Sistem latihan pada ibu jari menghasilkan pergerakan otot dalam empat postur iaitu: 0°, 30°, 60°, dan 90°. Isyarat terkumpul dari HD-sEMG berasal dari kedua-dua lengan tangan anterior dan posterior dari 17 peserta telah diklasifikasi dengan cekap menggunakan rangkaian neural dengan ketepatan 100% dan min kuasa dua ralat (MSE) sebanyak 1.4923 x 10-5 berdasarkan setdata yang diuji. Klasifikasi sempurna ini dicapai dengan menggunakan teknik latihan aturan rambatan-belakang Bayesian (trainbr), mengguna pakai tujuh lapisan tersembunyi dengan gabungan latihan-validasi-ujian mengikut kadar 70-15-15. Pada masa hadapan, pengkaji boleh menerokai potensi integrasi mekanisme tindak balas nyata dalam meramal dan mengenali kontraksi otot ibu jari. Integrasi ini mungkin membolehkan pengalaman interaksi antara peranti prostetik dan pengguna.
•Fast-ICA can extract the motor unit activities in dynamic and isometric tasks.•The motor unit synchronization increases significantly after Bicep muscle fatigue.•Bicep muscle fatigue mechanism does ...not vary due to different contraction tasks.
The fatigue-induced neuromuscular mechanism remains to be fully elucidated. So far, the macroscopic mechanism using global surface electromyogram (sEMG) has been widely investigated. However, the microscopic mechanism using high-level neural information based on motor unit (MU) spike train from the spinal cord lacks attention, especially for the conditions under dynamic contraction task. The synchronization of the MU spike train is generally assumed to be an excellent indicator to represent the activities of spinal nerves. Accordingly, this study employed synchronization of MU spike train decomposed from high-density sEMG (HD-sEMG) to investigate the fatigue condition in muscular contractions within the Biceps Brachii muscle under both isometric and dynamic contraction tasks, giving a complete picture of the microscopic fatigue mechanism. We compared the synchronization of MU in Delta (1–4 Hz), alpha (8–12 Hz), Beta (15–30 Hz), and Gamma (30–60 Hz) frequency bands during the fatigue condition induced by different contractions. Our results showed that MU synchronization increased significantly (p<0.05) in all frequency bands across the two contraction tasks. The results indicate that the microscopic fatigue mechanism of Biceps Brachii muscle does not vary due to different contraction tasks.
Enhancing information security via reliable user authentication in wireless body area network (WBAN)-based Internet-of-Things (IoT) applications has attracted increasing attention. The ...noncancelability of traditional biometrics (e.g., fingerprint) for user authentication increases the privacy disclosure risks once the biometric template is exposed, because users cannot volitionally create a new template. In this work, we propose a cancelable biometric modality based on high-density surface electromyogram (HD-sEMG) encoded by hand gesture password, for user authentication. HD-sEMG signals (256 channels) were acquired from the forearm muscles when users performed a prescribed gesture password, forming their biometric token. Thirty four alternative hand gestures in common daily use were studied. Moreover, to reduce the data acquisition and transmission burden in IoT devices, an automatically generated password-specific channel mask was employed to reduce the number of active channels. HD-sEMG biometrics were also robust with reduced sampling rate, further reducing power consumption. HD-sEMG biometrics achieved a low equal error rate (EER) of 0.0013 when impostors entered a wrong gesture password, as validated on 20 subjects. Even if impostors entered the correct gesture password, the HD-sEMG biometrics still achieved an EER of 0.0273. If the HD-sEMG biometric template was exposed, users could cancel it by simply changing it to a new gesture password, with an EER of 0.0013. To the best of our knowledge, this is the first study to employ HD-sEMG signals under common daily hand gestures as biometric tokens, with training and testing data acquired on different days.
Objective: We describe and test the methodology supporting the identification of individual motor unit (MU) firings in the motor response (M wave) to percutaneous nerve stimulation recorded by ...surface high-density electromyography (HD-EMG) on synthetic and experimental data. Methods: A set of simulated voluntary contractions followed by 100 simulated M waves with a normal distribution (MU mean firing latency: 10 ms, Standard Deviation - <inline-formula><tex-math notation="LaTeX">\rm{SD_{LAT}}</tex-math></inline-formula> 0.1-1.3 ms) constituted the synthetic signals. In experimental condition, at least 52 progressively increasing M waves were elicited in the soleus muscle of 12 males, at rest (REST), and at 10% (C10) and 20% (C20) of maximal voluntary contraction (MVC). The MU decomposition filters were identified from 15-20 s long isometric plantar flexions performed at 10-70% of MVC and, afterwards, applied to M waves. Results: Synthetic signal analysis demonstrated high accuracy of MU identification in M waves (precision ≥ 85%). In experimental conditions 42.6 ± 11.2 MUs per participant were identified from voluntary contractions. When the MU filters were applied to the M wave recordings, 28.4 ± 14.3, 23.7 ± 14.9 and 20.2 ± 13.5 MU firings were identified in the maximal M waves, with individual MU firing latencies of 10.0 ± 2.8 (<inline-formula><tex-math notation="LaTeX">\rm{SD_{LAT}}</tex-math></inline-formula>: 1.2 ± 1.2), 9.6 ± 3.0 (<inline-formula><tex-math notation="LaTeX">\rm{SD_{LAT}}</tex-math></inline-formula>: 1.5 ± 1.3) and 10.1 ± 3.7 (<inline-formula><tex-math notation="LaTeX">\rm{SD_{LAT}}</tex-math></inline-formula>: 1.7 ± 1.6) ms in REST, C10 and C20 conditions, respectively. Conclusion and significance: We present evidence that supports the feasibility of identifying MU firings in M waves recorded by HD-EMG.
Surface electromyogram (sEMG) based hand gesture recognition for prosthesis or armband is an important application of the human-machine interface. However, the measurement location of sensors greatly ...influences the hand gesture performance, especially with the inter-day or inter-subject validation protocols. Therefore, we acquired two-day hand gesture data of 41 subjects with a 256 (16×16) channel high-density sEMG electrode array. With the acquired data, we initially compared the support vector machine (SVM) and other four state-of-art classifiers under three validation protocols, i.e., intra-day, inter-day and inter-subject validation protocols. Then, we screened 14 feature optimization techniques, including 5 feature-projection methods and 9 feature-ranking approaches. To present the accuracy tendency with varying measure locations, we systematically explored the 10-hand gesture performance using data of 16 prosthesis measurement locations (PMLs) and 15 armband measurement locations (AMLs). As a result, the SVM classifier was suitable for the intra-day and inter-day validation protocols and the 2-dimensional convolutional neural network was selected for the inter-subject validation protocol. The mean accuracies of the hand gesture classification ranged from 95.68% to 99.12% (intra-day validation), from 68.41% to 88.02% (inter-day validation) and from 63.39% to 86.33% (inter-subject validation) for the prosthesis application. In addition, for the armband application, the mean accuracies ranged from 96.25% to 97.43% (intra-day validation), from 67.44% to 75.83% (inter-day validation) and from 65.53% to 75.40% (inter-subject validation). The accuracy is greatly correlated with the measurement location, which is highly associated with the neuromuscular structures of human bodies. In summary, our work can serve as a factor-screening tool for users customizing their systems according to their physical conditions and requirements.
Although surface electromyogram recorded from high-density electrode array is believed to carry sufficient spatial information that can benefit the decoding of motor intentions, the complexity of ...using the array hindered its widespread applications especially in wearable devices. This study is aimed to develop a non-acoustic modality of silent speech recognition that transfers knowledge learned from high-density array to a system using a few channels, with both high portability and performance. A convolutional neural network was established for recognizing a vocabulary of 33 Chinese words during subvocal speech production. The network was trained by the data recorded from face and neck muscles using two arrays with 64 channels in the source domain. Then it was calibrated through a transfer learning approach to grant its adaption to a new target domain with the data recorded by 8 separated electrodes, while its good capability of characterizing subvocal speech word patterns is expected to be maintained. The proposed method significantly outperformed three common classification approaches and the baseline approach without transfer learning (a network trained with data just from the target domain). Under conditions of electrode shift and cross-user variability, it still obtained performance improvements. The method is demonstrated to be viable for transfer learning across domains of electrode settings and it facilitates to improve the performance of silent speech recognition systems using separate electrode sites under the guidance from high-density of arrays.
Robotic assistant-based therapy holds great promise to improve the functional recovery of stroke survivors. Numerous neural-machine interface techniques have been used to decode the intended movement ...to control robotic systems for rehabilitation therapies. In this case report, we tested the feasibility of estimating finger extensor muscle forces of a stroke survivor, based on the decoded descending neural drive through population motoneuron discharge timings. Motoneuron discharge events were obtained by decomposing high-density surface electromyogram (sEMG) signals of the finger extensor muscle. The neural drive was extracted from the normalized frequency of the composite discharge of the motoneuron pool. The neural-drive-based estimation was also compared with the classic myoelectric-based estimation. Our results showed that the neural-drive-based approach can better predict the force output, quantified by lower estimation errors and higher correlations with the muscle force, compared with the myoelectric-based estimation. Our findings suggest that the neural-drive-based approach can potentially be used as a more robust interface signal for robotic therapies during the stroke rehabilitation.
Upper extremity (UE) neuromuscular dysfunction critically affects post-stroke patients from performing activities of daily life. In this regard, various rehabilitation robotics have been developed ...for providing assistive and/or resistive forces that allow stroke survivors to train their arms towards regaining the lost arm function. However, most of the rehabilitation systems function in a passively such that they only allow patients navigate already-defined trajectories that often does not align with their UE movement intention, thus hindering adequate motor function recovery. One possible way to address this problem is to use a decoded UE motion intent to trigger active and intuitive motor training for the patients, which would help restore their UE arm functions. In this study, a new approach based on spatiotemporal neuromuscular descriptor and adaptive filtering technique (STD-AFT) is proposed to optimally characterize multiple patterns of UE movements in post-stroke patients towards providing inputs for intelligently driven motor training in the rehabilitation robotic systems. The proposed STD-AFT performance was systematically investigated and assessed in comparison with commonly adopted methods via high-density surface electromyogram recordings obtained from post-stroke survivors who performed 21 distinct classes of pre-defined limb movements. Furthermore, the movement intent decoding was done using four different classification algorithms. The experimental results showed that the proposed STD-AFT achieved significant improvement of up to 13.36% (
p
< 0.05) in characterizing the multiple patterns of movement intents with relatively lower standard-error value even in the presence of the external interference in form of noise compared to the existing benchmark methods. Also, the STD-AFT showed obvious pattern seperability for individual movement class in a two-dimensional space. The outcomes of this study suggest that the proposed STD-AFT could provide potential inputs for active and intuitive motor training in robotic systems targeted towards stroke-rehabilitation.