ECG is an essential diagnostic tool that offers important insight into a person's cardiac and general health. The rise of intelligent wearable devices has opened a new avenue for clinicians and individuals to capture long term ECG data—albeit with fewer leads than the 12 leads that are typically used clinically, which can be vital for identifying and addressing health concerns. In this work, a multi-task convolutional neural network (CNN) classifier was used to study the influence of various combinations of ECG leads in interpretation of 71 cardiac statements spanning cardiac diagnostics, form, and rhythm. Results of this analysis suggest that the subset of limb leads I and II and chest leads V1, V3, and V6 can be used to identify several cardiac statements without loss of performance (average macro AUC of 0.903) when compared to a model trained using all 12- leads (average macro AUC of 0.905; p = 1). A hybrid CNNLSTM (long short-term memory) model was developed to reconstruct the missing chest leads. The highest performing lead reconstructor achieved an average R2 score of 0.835 when reconstructing three chest leads. This architecture was proposed as the foundation for a wearable system that could record a limited number of ECG leads while also providing a 12-lead ECG for clinical applications.

Wearable devices have begun to incorporate machine learning models to assist with detection of various cardiac conditions. In this work, we developed a multi-task convolutional neural network to simultaneously predict$\mathbf{7 5}$diagnostic, form and rhythm statements from 10-s duration, 12-lead ECGs. The model, originally developed off-line in TensorFlow, was converted to the FlatBuffers format for on-edge AI using the LiteRT toolset. Posttraining quantization was used to compare different numerical precisions in terms of model size, model performance and inference time. Classifier performance for the 12-lead configuration was consistent between the 32-bit floating point model (“float32” baseline), the dynamic range quantized model (DR) and the float16 model$(p=0.92)$with an average macro AUC score of 0.893 with all output statements considered. A large degradation in classification performance was observed for 8-bit integer quantization (int8) which yielded an average macro AUC score of 0.513 for the 12-lead configuration across all statements. To address class imbalance, minority classes were removed. Reducing the number of statements to$\mathbf{4 1}$classes increased macro F1 score by an average of 72.6% (to a mean value about 0.358) for the float32, float16 and DR quantized models.

There has been significant growth in wearable wireless patient physiological monitoring over the last decade. Many applications require a real-time, low-latency, small profile, and low-power-battery system. In this work, various Bluetooth low energy (BLE) configurations were tested in a multi-channel, wireless system to determine the lowest peripheral power configuration and the number of supported peripherals for each BLE configuration. Using nodes that continuously sampled at 1 kHz, connection intervals from 10-100 ms and event lengths of 2500, 5000 and 7500 μs were tested. The lowest current consumption, 2.39 mA, was measured for a connection interval of 100 ms, event length of 2500 μs, and maximum transmission unit (MTU) of 247 bytes. The maximum number of supported peripheral connections was observed to be 11 for a connection interval of 100 ms, event lengths of 5000 and 7500 μs, and MTU size of 247 bytes. We found that using longer connection intervals led to decreases in power consumption and shorter event lengths allowed for support of more peripheral sensors nodes for a given connection interval, assuming the event length is long enough to transmit the desired amount of data. Future work should investigate techniques to optimize power consumption further and to extend the number of supported peripheral nodes.

Human–machine interaction requires accurate recognition of human intentions (e.g., via hand gestures). Here, we assessed the cross-day robustness of widely used hand gesture classification techniques applied to high-density surface electromyogram (HD-sEMG) signals (256 channels). Our evaluation covered techniques in each stage of the classification framework: first, 50 temporal-spectral-spatial domain features, second, 15 feature optimization techniques, and third, seven classifiers. Moreover, although HD-sEMG provides sufficient neuromuscular information, some of the channels may present low signal-to-noise ratio and should therefore be treated as outliers. Accordingly, we performed our evaluation with, first, all outlier channels retained, and second, removal of the features corresponding to poor-quality channels and substitution with interpolated values from neighbor channels. The impact of sliding window and data augmentation was also investigated. We examined the results on a 35-gesture classification task using HD-sEMG acquired from 20 subjects on two sessions in separate days. The results showed that interpolation of features from outlier channels significantly improved the performance in most cases. Use of a sliding window and of data augmentation contributed to a higher classification accuracy. For the classification of 11 selected gestures of common daily use, the support vector machine classifier achieved the highest classification accuracy of 91.9% in a cross-day validation protocol using an optimal combination of 13 features (each extracted from sliding windows), feature optimization by linear discriminant analysis, and data augmentation. Our work can serve as a technique-screening tool on cross-day applications of human–machine interactions.

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.

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.

The ability to expertly control different fingers contributes to hand dexterity during object manipulation in daily life activities. The macroscopic spatial patterns of muscle activations during finger movements using global surface electromyography (sEMG) have been widely researched. However, the spatial activation patterns of microscopic motor units (MUs) under different finger movements have not been well investigated. The present work aims to quantify MU spatial activation patterns during movement of distinct fingers (index, middle, ring and little finger). Specifically, we focused on extensor muscles during extension contractions. Motor unit action potentials (MUAPs) during movement of each finger were obtained through decomposition of high-density sEMG (HD-sEMG). First, we quantified the spatial activation patterns of MUs for each finger based on 2-dimension (2-D) root-mean-square (RMS) maps of MUAP grids after spike-triggered averaging. We found that these activation patterns under different finger movements are distinct along the distal-proximal direction, but with partial overlap. Second, to further evaluate MU separability, we classified the spatial activation pattern of each individual MU under distinct finger movement and associated each MU with its corresponding finger with Regularized Uncorrelated Multilinear Discriminant Analysis (RUMLDA). A high accuracy of MU-finger classification tested on 12 subjects with a mean of 88.98% was achieved. The quantification of MU spatial activation patterns could be beneficial to studies of neural mechanisms of the hand. To the best of our knowledge, this is the first work which manages to quantify MU behaviors under different finger movements.

With the soaring development of body sensor network (BSN)-based health informatics, information security in such medical devices has attracted increasing attention in recent years. Employing the biosignals acquired directly by the BSN as biometrics for personal identification is an effective approach. Noncancelability and cross-application invariance are two natural flaws of most traditional biometric modalities. Once the biometric template is exposed, it is compromised forever. Even worse, because the same biometrics may be employed as tokens for different accounts in multiple applications, the exposed template can be used to compromise other accounts. In this work, we propose a cancelable and cross-application discrepant biometric approach based on high-density surface electromyogram (HD-sEMG) for personal identification. We enrolled two accounts for each user. HD-sEMG signals from the right dorsal hand under isometric contractions of different finger muscles were employed as biometric tokens. Since isometric contraction, in contrast to dynamic contraction, requires no actual movement, the users' choice to login to different accounts is greatly protected against impostors. We realized a promising identification accuracy of 85.8% for 44 identities (22 subjects × 2 accounts) with training and testing data acquired 9 days apart. The high identification accuracy of different accounts for the same user demonstrates the promising cancelability and cross-application discrepancy of the proposed HD-sEMG-based biometrics. To the best of our knowledge, this is the first study to employ HD-sEMG in personal identification applications, with signal variation across days considered.

Existing commercial hand prostheses can be controlled from the electrical activity (electromyogram or EMG) of remnant muscle tissue within the forearm, but are limited in function to one degree of freedom of proportional control. In a pilot study (N=3 subjects), we used least squares estimation to identify a model between forearm electrical activity recorded by high-resolution (64 channel) electrode arrays (applied over the flexor and, separately, extensor muscles of the forearm) to force in the four fingertips. Average errors ranged from 4.21 to 10.20 %MVCF(flexion maximum voluntary contraction), depending on the muscle contraction task performed, number of EMG electrodes in the model and the electrode montage selected. Results suggest that, at least for intact subjects, 2-4 degrees of freedom of proportional control are available from the EMG signals of the forearm.