Towards Finger Gestures and Force Recognition Based on Wrist Electromyography and Accelerometers

Electromyogram (EMG) signals have been increasingly used for hand and finger gesture recognition. However, most studies have focused on the wrist and whole-hand gestures and not on individual finger (IF) gestures, which are considered more challenging. In this study, we develop EMG-based hand/finger gesture classifiers based on fixed electrode placement using machine learning methods. Ten healthy subjects performed ten hand/finger gestures, including seven IF gestures. EMG signals were measured from three channels, and six time-domain (TD) features were extracted from each channel. A total of 18 features was used to build personalized classifiers for ten gestures with an artificial neural network (ANN), a support vector machine (SVM), a random forest (RF), and a logistic regression (LR). The ANN, SVM, RF, and LR achieved mean accuracies of 0.940, 0.876, 0.831, and 0.539, respectively. One-way analyses of variance and F-tests showed that the ANN achieved the highest mean accuracy and the lowest inter-subject variance in the accuracy, respectively, suggesting that it was the least affected by individual variability in EMG signals. Using only TD features, we achieved a higher ratio of gestures to channels than other similar studies, suggesting that the proposed method can improve the system usability and reduce the computational burden.

Taste sensation recognition is valuable for developing virtual taste and the early diagnosis of taste system disorders. Electromyography (EMG) can characterize the information of taste sensation and have the advantages of a high signal-to-noise ratio and easy acquisition. This paper presents feature extraction and feature combination methods for taste sensation knowledge based on facial EMG. The time domain features, frequency domain features, time-frequency domain features, and entropy features are extracted as individual feature sets after data pre-processing. Combinations of different features are performed to acquire multivariate feature representations. Machine learning methods are used to predict taste sensation categories. The combination of the frequency domain, time-frequency domain, and entropy features as feature set and Random Forest method as classifier obtain the highest recognition accuracy. The results provide a reference for feature extraction and selection for basic taste sensation recognition.

PurposePenetration state is one of the most important factors for judging the quality of a gas tungsten arc welding (GTAW) joint. The purpose of this paper is to identify and classify the penetration state and welding quality through the features of arc sound signal during robotic GTAW process.Design/methodology/approachThis paper tried to make a foundation work to achieve on‐line monitoring of penetration state to weld pool through arc sound signal. The statistic features of arc sound under different penetration states like partial penetration, full penetration and excessive penetration were extracted and analysed, and wavelet packet analysis was used to extract frequency energy at different frequency bands. The prediction models were established by artificial neural networks based on different features combination.FindingsThe experiment results demonstrated that each feature in time and frequency domain could react the penetration behaviour, arc sound in different frequency band had different performance at different penetration states and the prediction model established by 23 features in time domain and frequency domain got the best prediction effect to recognize different penetration states and welding quality through arc sound signal.Originality/valueThis paper tried to make a foundation work to achieve identifying penetration state and welding quality through the features of arc sound signal during robotic GTAW process. A total of 23 features in time domain and frequency domain were extracted at different penetration states. And energy at different frequency bands was proved to be an effective factor for identifying different penetration states. Finally, a prediction model built by 23 features was proved to have the best prediction effect of welding quality.

To improve human-machine cooperation and enhance the accuracy of gait recognition in wearable lower limb exoskeletons, an enhancement method of gait recognition based on adaptive feature selection and an optimized machine learning algorithm was proposed. In this study, surface electromyography (sEMG) signals of rectus femoris, medialis femoris, lateralis femoris, semitendinosus and biceps femoris were recorded during level-ground walking. Then, time domain, frequency domain, time-frequency domain and nonlinear features were extracted. The integrated value of electromyography, variance, root mean square and wavelength were selected as the time domain features, and the mean power frequency and median frequency were selected as the frequency domain features. Wavelet packet energy was selected as the time-frequency domain feature. Nonlinear features including approximate entropy, sample entropy and fuzzy entropy of sEMG were extracted. To reduce feature dimension and improve the calculation efficiency, adaptive feature selection was performed by particle swarm optimization combined with sigmoid function. Then, the feature matrix was determined as the input for a random forest classifier to recognize different gait phases. An adaptive optimization mechanism based on Bayesian optimization was applied to random forest. Compared with random forest, the overall performance of the optimized model was improved. Its accuracy was increased by 3.57%. The feature selection and adaptive optimization mechanisms in gait recognition not only enhance the accuracy of random forest algorithms applied to sEMG for gait prediction, but also facilitate the flexibility and consistency required for lower limb exoskeleton gait control.

The objective of this study was to determine whether a novel technique using high density surface electromyogram (EMG) recordings can be used to detect the directional dependence of muscle activity in a multifunctional muscle, the first dorsal interosseous (FDI). We used surface EMG recordings with a two-dimensional electrode array to search for inhomogeneous FDI activation patterns with changing torque direction at the metacarpophalangeal joint, the locus of action of the FDI muscle. The interference EMG distribution across the whole FDI muscle was recorded during isometric contraction at the same force magnitude in five different directions in the index finger abduction–flexion plane. The electrode array EMG activity was characterized by contour plots, interpolating the EMG amplitude between electrode sites. Across all subjects the amplitude of the flexion EMG was consistently lower than that of the abduction EMG at the given force. Pattern recognition methods were used to discriminate the isometric muscle contraction tasks with a linear discriminant analysis classifier, based on the extraction of two different feature sets of the surface EMG signal: the time domain (TD) feature set and a combination of autoregressive coefficients and the root mean square amplitude (AR+RMS) as a feature set. We found that high accuracies were obtained in the classification of different directions of the FDI muscle isometric contraction. With a monopolar electrode configuration, the average overall classification accuracy from nine subjects was 94.1 ± 2.3% for the TD feature set and 95.8 ± 1.5% for the AR+RMS feature set. Spatial filtering of the signal with bipolar electrode configuration improved the average overall classification accuracy to 96.7 ± 2.7% for the TD feature set and 98.1 ± 1.6% for the AR+RMS feature set. The distinct EMG contour plots and the high classification accuracies obtained from this study confirm distinct interference EMG pattern distributions as a function of task direction, suggesting that high density surface EMG is a useful tool for understanding the activation of multifunctional muscles.

With the increasing awareness of health, using wearable sensors to monitor individual activities and accurately estimate energy expenditure has become a current research focus. However, existing research encounters challenges including low estimation accuracy, a deficiency of frequency domain features, and difficulty in integrating time domain and frequency domain features. To address these issues, we propose an innovative framework called the Dual-Stream Fusion Network (DSFN). This framework combines the Time Domain Encoding (TDE) module, the Frequency Domain Hierarchical-Split Encoding (FDHSE) module, and a Two-Stage Feature Fusion (TSF) module. Specifically, the temporal stream of the framework employs the TDE module to capture deep temporal features that reflect the complex dynamic variations in time-series data. The frequency domain stream introduces the FDHSE module, which extracts frequency domain features using a multi-level, multi-scale approach, ensuring a comprehensive and diverse representation of frequency information. Through this dual-stream architecture, our model effectively learns both time and frequency domain features, addressing the limitations of frequency domain features observed in prior studies. Additionally, we propose the TSF module to fully integrate time and frequency domain features, effectively overcoming the challenge of fusing these two types of features. We conducted experiments on two public datasets, namely the GOTOV dataset (elderly people) and the JSI dataset (young people). Experimental results demonstrate that our method achieves excellent performance across different age groups. Compared to the baseline models, the proposed DSFN significantly improves the accuracy of human energy expenditure estimation.

Objectives: To facilitate painless and easy method for prediction of diabetes with high accuracy and to measure blood glucose by noninvasive method using Photoplethysmography (PPG). Method: In this study, diabetes prediction is done using different machine learning algorithms on a dataset created by using samples from PIMA Indian Diabetes dataset and in vivo diabetes dataset. Machine learning algorithms used are Support Vector Machine (SVM), Decision Tree, Naïve Bayes Classifier and K Nearest Neighbor (KNN). A PPG data of 182 individuals is recorded over 1 minute duration each. Various frequency and time domain features of PPG single are extracted using single pulse wave analysis. Neural network is trained using extracted features and glucose measurement is performed. Findings: With decision tree algorithm we got highest accuracy of 89.97% for diabetes prediction and it proves to be good algorithm for consideration for measurement in diabetes treatment.Clarke Error Grid analysis for blood glucose prediction is clinically accepted, so we performed similar analysis. Using time and frequency domain features, we got 94.27 % data points in clinically accepted regions (Region A and Region B). Novelty: Based on the data collected or samples analyzed, and accuracy of our results, it is encouraging to see that further research may lead to affordable noninvasive method for detection of diabetes at early stage. Keywords: Noninvasive; blood glucose; NIR; machine learning algorithms; photoplethysmography

In physiological signal analysis, identifying meaningful relationships and inherent patterns in signals can provide valuable information regarding subjects' physiological state and changes. Although MATLAB has been widely used in signal processing and feature analysis, Python has recently dethroned MATLAB with the rise of data science, machine learning and artificial intelligence. Hence, there is a compelling need for a Python package for physiological feature analysis and extraction to achieve compatibility with downstream models often trained in Python. Thus, we present a novel visualization and feature analysis Python toolbox, PySio, to enable rapid, efficient and user-friendly analysis of physiological signals. First, the user should import the signal-of-interest with the corresponding sampling rate. After importing, the user can either analyze the signal as it is, or can choose a specific region for more detailed analysis. PySio enables the user to (i) visualize and analyze the physiological signals (or user-selected segments of the signals) in time domain, (ii) study the signals (or user-selected segments of the signals) in frequency domain through discrete Fourier transform and spectrogram representations, and (iii) investigate and extract the most common time (energy, entropy, zero crossing rate and peaks) and frequency (spectral entropy, rolloff, centroid, spread, peaks and bandpower) domain features, all with one click. Clinical relevance- As the physiological signals originate directly from the underlying physiological events, proper analysis of the signal patterns can provide valuable information in personalized treatment and wearable technology applications.

To improve the human-machine cooperativity of a wearable lower limb exoskeleton, a gait recognition method based on surface electromyography (sEMG) was proposed. sEMG of rectus femoris, vastus medialis, vastus lateralis, semitendinosus and biceps femoris were acquired. Then, time domain, frequency domain, time-frequency domain and nonlinear features were extracted. The integrated value of electromyography, variance, root mean square and wavelength were selected as the time domain features and the frequency domain feature includes mean power frequency. Wavelet packet energy was selected as the time-frequency domain feature. Nonlinear features including approximate entropy, sample entropy and fuzzy entropy of sEMG were extracted. Classification accuracy of different feature matrices and different muscle groups were constructed and verified. The optimal multi-dimensional fusion feature matrix was determined. Introducing the Bayesian optimization algorithm, the Bayesian optimized Random Forest classification model was constructed to identify different gait phases. Comparing with Random Forest, the accuracy of the optimized Random Forest was improved by 5.89%. Applying Random Forest algorithm with Bayesian optimization to gait prediction based on sEMG, the followership and consistency of gait control in lower limb exoskeleton can be improved. This template explains and demonstrates how to prepare your camera-ready paper for Trans Tech Publications. The best is to read these instructions and follow the outline of this text.

A novel multi-channel-based 3D convolutional neural network (3D-CNN) is proposed in this paper to classify sleep stages. Time domain features, frequency domain features, and time-frequency domain features are extracted from electroencephalography (EEG), electromyogram (EMG), and electrooculogram (EOG) channels and fed into the 3D-CNN model to classify sleep stages. Intrinsic connections among different bio-signals and different frequency bands in time series and time-frequency are learned by 3D convolutional layers, while the frequency relations are learned by 2D convolutional layers. Partial dot-product attention layers help this model find the most important channels and frequency bands in different sleep stages. A long short-term memory unit is added to learn the transition rules among neighboring epochs. Classification experiments were conducted using both ISRUC-S3 datasets and ISRUC-S1, sleep-disorder datasets. The experimental results showed that the overall accuracy achieved 0.832 and the F1-score and Cohen's kappa reached 0.814 and 0.783, respectively, on ISRUC-S3, which are a competitive classification performance with the state-of-the-art baselines. The overall accuracy, F1-score, and Cohen's kappa on ISRUC-S1 achieved 0.820, 0.797, and 0.768, respectively, which also demonstrate its generality on unhealthy subjects. Further experiments were conducted on ISRUC-S3 subset to evaluate its training time. The training time on 10 subjects from ISRUC-S3 with 8549 epochs is 4493s, which indicates its highest calculation speed compared with the existing high-performance graph convolutional networks and [Formula: see text]Net architecture algorithms.

A comparative analysis of electromyogram (EMG) signals of patients of cervical pain and normal controls. To determine the differences between frequency and time domain parameters of EMG signals of patients of cervical pain and normal controls. No diagnostic technique has emerged as a satisfactory tool for identification of spinal pain. Seventeen male and 17 female chronic neck pain patients without cervical radiculopathy were recruited through neurology EMG clinic. The controls consisted of 30 male and 33 female subjects with no history of neck pain in the past 12 months. All subjects performed flexion, left anterolateral flexion, left lateral flexion, left posterolateral extension, and extension to pain threshold/20% maximum voluntary contraction and pain tolerance/maximum voluntary contraction in random order. The descriptive statistics for body weight normalized strength, normalized peak EMG, time to onset, time to peak, median frequency, mean power frequency, and frequency bands were calculated. These variables were subjected to analysis of variance and logistic regression to distinguish between patients and controls. The normalized peak EMG of patients was significantly greater than those of controls in both maximal and submaximal exertions (P < 0.01). Whereas there was no consistent pattern in time to peak EMG, the time to onset of EMG revealed that the left sternocleidomastoid was always recruited before the onset of torque. A lack of significant difference in the median frequency of the 2 samples indicates that the pain did not disturb the muscle conduction velocity. Using discriminant logistic regression on frequency domain and time domain parameters, up to 97% of patients and controls were correctly classified with the resubstitution method. Surface EMG can be used successfully in distinguishing chronic pain patients and controls, and efficacy of treatment regimes.

Support Vector Machine (SVM) is an important machine learning algorithm widely used for the development of machine fault diagnosis systems. In this work, we use an SVM back-end classifier, with statistical features in time and frequency domain as its input, for the development of a fault diagnosis system for a rotating machine. Our baseline system is evaluated for its speed dependent and speed independent performances. In this paper, we use locality constrained linear coding (LLC) to map the input feature vectors to a higher dimensional linear space, and remove some of the speed specific dimensions to improve the speed independent performance of the fault diagnosis system. We use LLC to do the feature mapping to the higher dimensional space, and select only the k nearest neighbour basis vectors to represent the input feature vector and thus reduce/minimize the effect of speed specific factors from the input feature vector, and thus improve the speed independent performance of the fault diagnosis. We compare the performance of the LLC-SVM system for the time and frequency domain statistical features. The proposed approach has improved the overall classification accuracy by 11.81% absolute for time domain features and 10.53% absolute for frequency domain features compared to the baseline speed independent system.

In this paper, based on the wireless acceleration sensor, a wearable body data acquisition system is designed. The acceleration vector magnitude and the angular velocity vector amplitude signal are selected as the breakthrough of the body posture recognition. The focus is on the classification algorithms of the 10 body types commonly used by the soldiers, including Qi Bu walking, goose step, running, low posture, side posture, high posture, push-ups, sit-ups, upstairs and downstairs. The time domain features, frequency domain features and time-frequency characteristics of the signals are analysed respectively. The high-dimensional mixed feature vectors are extracted and reduced by LDA. A support vector machine algorithm based on hybrid features is proposed. The algorithm has been verified by experiments and achieved ideal results.

to the editor: The electromyogram (EMG) as an indirect measure of motor unit activity has proved invaluable in motor control studies. Increasingly, the application of frequency domain techniques to EMG signals has provided important insight into the structure and function of the human motor system.

Long-term time series forecasting by combining local periodic change features in frequency domain and global features in time domain