1. Introduction
Over the past few decades, the field of Human Machine Interfaces (HMI) has attracted increasing interest due to its intuitive applications in the medical field. Researchers have explored signals on humans, including electroencephalography (EEG), electrocorticography (ECoG), mechanomyography (MMG) and surface electromyography (sEMG). The EEG signal has considerable practical value due to its non-invasiveness, but its signal-to-noise ratio (SNR) is low and susceptible to external interference [
1]. The ECoG signal is an invasive signal, for which electrodes need to be implanted into the cerebral cortex. It has limited access to nerve information and can even cause consistent harm to the human body [
2]. Compared to the previous two types of signals, MMG has the benefit of being unaffected by skin surface impedance or electrode displacement. However, its limitations include poor SNR and sensitivity to external noise [
3]. Therefore, sEMG was chosen as the acquisition signal in this study.
The sEMG signal reflects the nerve activity state and is related to limb movement. During limb movement, the corresponding neural information can be obtained by back pushing sEMG signal, which has the advantages of non-invasive acquisition and bionics [
4,
5]. Therefore, in the past few decades, the sEMG signal has become the most popular choice for developing intuitive human-machine interfaces [
6] and has been widely used in medical applications, virtual reality interfaces, nerve rehabilitation, prosthetic control, etc. [
7,
8,
9].
The form of human muscle contraction can be divided into two categories: static and dynamic contraction. During static contraction, the length of muscle fibers does not change, and the joints do not move, but muscle fibers remain at the state of contraction [
5]. Conversely, during dynamic contraction, the length of muscle fibers changes, and the joints continue to move. Therefore, the research field of motion decoding based on the sEMG signal can also be roughly divided into two categories. The first is to research the discrete motion which corresponds to static contraction of muscles through sEMG signal, such as keeping hands still or making the peace sign [
10,
11]. The second is to use the sEMG signal to predict the continuous motion changes of the joint which corresponds to the dynamic contraction of muscles, such as changes of joint torque and joint angle [
12,
13,
14].
With the exploration of continuous movement still in its infancy, there is a lot of potential of advance in the future [
15]. Therefore, classification accuracy improvement and prediction time reduction in gesture decoding remain the most researched issues in the sEMG signal field [
16,
17]. This paper explored only the decoding of discrete movements of limbs through sEMG signal. Discrete motion classification is currently the most mature and fruitful method in the field of human action decoding, based on sEMG.
The representative papers in recent years are as follows: Min et al. [
18] proposed a cross individual gesture decoding method based on Long Short-Term Memory network (LSTM)—Cross individual dual network structure (CI-LSTM) in 2021. Compared with other algorithm models, the decoding accuracy of the model was improved by 9.15% on average. Wang et al. [
19] used a genetic algorithm to optimize the number of signal channels and concluded that using 11 of the 16 channels can achieve 97% of the best performance of gesture decoding. Additionally, placing the electrodes in the middle of the forearm, rather than in the proximal forearm, can result in better performance. Ulysse et al. [
20] applied deep learning approach to the field of gesture decoding and proposed a new migration learning scheme using convolutional neural networks, which achieved 98.31% offline decoding accuracy for 7 gestures of more than 17 participants and 68.98% offline decoding accuracy for 18 gestures of more than 10 participants. Anany et al. [
12] researched the continuous decoding of forearm motion in 2019 and discovered that subject specific, hand specific and object specific decoding models offer better decoding accuracy than generic models. Additionally, Adewuyi et al. [
21] analyzed the contribution of internal and external hand muscles to finger motion classification. The research showed that combining internal muscles’ sEMG data and wrist motions can significantly improve the robustness of gesture decoding.
Although the above research works have achieved promising results, most of those training and testing data were mixed in one or several days. Moreover, most of them focused on the design of appropriate channel number, feature set and classification model. However, human limb movement is a joint movement of muscles and bones controlled by the nervous system. Studies [
22] have shown that different individuals have different habitual exercise patterns, and even the same person has different models of motions under different external, physical and psychological conditions. In addition, the time and frequency features of the sEMG change with the thickness and temperature of the skin, thickness of the fat between the muscle and the skin, velocity of the blood flow and location of the sEMG sensors [
23]. However, the majority of the literature presented in this paper did not investigate the impact of the change of these elements on gesture decoding.
Based on this, three influencing elements were designed in this paper, namely, muscle fatigue, forearm angle and acquisition time. These elements are the most common negative factors influencing gesture decoding, based on sEMG. When the arms are held at the same position maintaining one gesture, these active tightened muscles fatigue quickly [
24], and the position of the forearm is accidentally modified to induce forearm angle changes [
25]. Moreover, exploring the impact of varied sEMG signal acquisition times on gesture decoding accuracy is critical for sEMG signal robustness [
26].
In order to train the classification model considering these three elements, individuals were instructed to make the same gesture in different periods, different forearm angles and different muscle fatigue levels. The control variable method was then used to validate the classification accuracy of the model to compare the negative impact of these elements on gesture decoding.
The rest of this paper is organized as follows: the experimental apparatus, muscle selection, forearm angle, gesture selection and experimental settings are described in
Section 2. The feature extraction and classification methods used in this experiment are reported in
Section 3. The results of impact of three influencing elements for classification accuracy are discussed in
Section 4. Finally,
Section 5 concludes the paper and presents further research directions.
2. Apparatus and Experiments
The experiments were performed by five able-bodied subjects, namely, three males and two females, age = 23 ± 2, with their dominant hand. All five subjects were right hand dominant. Before the experiment, all subjects were informed about the experiment and provided the informed consent. The testing procedure was in accordance with the declaration of Helsinki.
2.1. Apparatus
The sEMG signal of the forearm was collected by a Myon Aktos-mini EMG amplifier (Cometa company, Milan, Italy) (
Figure 1). The apparatus used disposable gel electrodes (H124SG) to attach to the target muscles. The gel electrodes can provide lower skin contact impedance, reduce the influence of external interference source and improve the signal-to-noise ratio, compared to dry electrodes [
4]. The sampling rate of the sEMG amplifier was 2000 Hz, and the Butterworth filter (20–500 Hz) was used for bandpass filtering.
2.2. Muscle Selection
Since the experimental apparatus has four double electrode channels, based on previous experience and reference [
27], four specific muscles were chosen for placing gel electrodes in all subjects: superficial flexor digitorum (SFD), which plays a role in finger bending except for the thumb and works in internal flexion of the wrist joint; flexor carpi ulnaris (FCU), which contracts in internal rotation of the wrist, downward wrist deviation, and elbow joint flexion; extensor carpi radialis longus (ECRL), which acts in wrist external rotation, wrist upward deviation and elbow extension; and finger extensor (FE), which works in finger extension and wrist extension except for the thumb (
Figure 2).
2.3. Forearm Angle
The elbows of all subjects were placed on the table when they performed gesture movements, so the forearm angle referred to the angle between the forearm and the tabletop. In order to comprehensively analyze the negative impact of the angle on the sEMG signal from small angle difference and large angle difference, the forearm angle range and the quality of sEMG signal typically utilized in actual gesture decoding were also considered. In this paper, three forearm angles were selected, namely, 30°, 45° and 75° (
Figure 3). During the experiment, the upper and lower angle deviation did not exceed ± 5°.
2.4. Gesture Selection
In practice, hand movements can be roughly divided into three categories according to the strength and type of muscle contraction [
27,
28]: (1) basic hand movements: hand closing (HC) and hand opening (HO); (2) wrist movements: wrist flexion (WF), wrist extension (WE), ulnar deviation (UD) and radial deviation (RD); (3) finger movements: thumb touches index finger (TI), middle finger (TM), ring finger (TR), little finger (TL), and the five fingertips touch (FL) (
Figure 4). These hand movements basically cover the common gestures in daily life. In addition, there was a relax gesture (RE) as a reference, which was not analyzed.
2.5. Experimental Setting
Each subject was provided with a motion instruction regarding how the experimental task was to be performed. For all experiments, subjects sat up straight, put their elbow on the table, exerted slight force on their arms, and tried to retain the force of each hand movement as consistent as possible.
The sEMG signal was sampled for five consecutive days, with an interval of one day for each sampling. Therefore, the signal data were measured three times totally, and were divided into categories , and . Forearm angles were also divided into 30°, 45°, and 75° respectively. Starting from the relaxation gesture, each gesture lasted for 5 s, and the interval between each gesture was 10 s. A group of 11 gestures was made up the normal muscle group and recorded as Class ; then, restarting in a short time from the relaxation gesture, each gesture lasted for 15 s, and there was no interval between each gesture. A group of 11 gestures was made up the fatigue muscle group, regarded as Class .
Regarding muscle fatigue, it has been demonstrated that as muscle fatigue continues, the frequency domain power spectrum shifts to the low frequency direction [
24]. At the same time, the time domain feature RMS will increase, and Mean Power Frequency (MPF) feature of the frequency domain will decrease [
29,
30]. As a result, these two eigenvalues have been frequently used as sensitive muscle tiredness indicators.
In this paper, all subjects were performed the muscle fatigue verification experiment at a 45° forearm angle according to the experimental description above; then, the power spectrum of the sEMG signal was analyzed, as shown in
Figure 5. Due to paper space limitations, one of each type of gestures of one subject was chosen as the representation, namely, HO, UD and TM. Additionally, the RMS and MPF features of each gesture of same subject were analyzed (
Table 1). The results show that the spectrum of fatigued muscle group (Class
) goes to the left when compared to the spectrum of normal muscle group (Class
), indicating that the power spectrum shifts to the low frequency during muscular exhaustion. Moreover, the RMS and FPM values in
Table 1 increased and decreased, respectively, indicating the presence of muscular exhaustion.
It must also be noted that due to factors such as gesture delay and error, when extracting valid gesture data, the first second and last second of each sampling were discarded, and only the middle three seconds were retained as valid data in Class , and only 12–14 s were retained as valid data in Class .
In order to avoid muscle accumulated fatigue, the relaxation time after each Class
and Class
was ten minutes. Taking into account three different issues, 18 types of datasets could be obtained, and each type of dataset had five groups. The detailed dataset classification is shown in
Table 2.
4. Results and Discussions
In the practical application of gesture decoding based on the sEMG signal, trained classification models have never used a validation dataset. In order to fit the accuracy of the actual classification model for gesture decoding, the commonly used cross validation method (dividing the dataset into k mutually exclusive subsets of similar size, then successively selecting the union of k-1 subsets as the training set and the remaining subsets as the test set) was not employed; instead, the method in which the training and testing datasets are completely separated from each other was used (data from the testing dataset were not used for training). Furthermore, the results were the mean values obtained by disrupting the data cycle training ten times. Additionally, decoding accuracy was selected as validation metric.
4.1. Influence of Muscle Fatigue
In this section, Class
datasets trained models were used to test Class
and Class
datasets, respectively, to obtain the effect of muscle fatigue on the accuracy of gesture decoding. At the same time, Class
datasets trained models were used to test Class
and Class
datasets, respectively. Results are shown in
Figure 9.
The results obtained by the two models using Class
and Class
as both training and testing datasets, respectively, were close, and average decoding accuracies were approximately 95%. When using Class
to test Class
and Class
to test Class
, the results obtained by the two models were also close. However, compared to the first two types of models, a considerable reduction was observed in the average decoding accuracies, which were close to 88%. In addition, decoding accuracy rates fluctuated greatly, with a maximum gap of nearly 15%. This pointed to the effect muscle fatigue has on the accuracy of gesture decoding, making it unstable. Additionally, a Pearson correlation analysis was performed on each subject to verify the universality of the influence of muscle fatigue on the model (
Table 3). When compared to using Class
datasets for both training and testing, using Class
datasets for both training and testing datasets instead resulted in lower correlation coefficient R values. This could be related to the fact that muscle fatigue in each participant was unpredictable. Nevertheless, almost all R values were higher than 0.4. Most of the R values of Class
to Class
and Class
to Class
in each subject were over 0.5.
4.2. Influence of Forearm Angle
The results from the previous section showed that muscle fatigue had an impact on the accuracy of gesture decoding. Furthermore, under same conditions, when using Class and Class as training and testing datasets, respectively, while using Class to test Class and Class to test Class , the results were close. Therefore, it is reasonable to assume that when comparing the effect of forearm angle and acquisition time on the classification models, the accuracies of using single Class or Class datasets will be similar. Here, only Class datasets were used in this section, for paper limitation reasons.
To avoid the influence of signal acquisition time, the training datasets and corresponding testing datasets were collected on the same day. The datasets with forearm angles of 30°, 45° and 75° collected in three days were used to test the datasets with forearm angles of 30°, 45° and 75° collected on the same day. The results are shown in
Figure 10.
The results of the above two classification models showed that when using same angle data for both training and testing, the accuracies of the two models were the highest. However, the greater the gap of forearm angle was the lower the decoding accuracy. For instance, when 30° of forearm angle was used as training dataset and 45° and 75° as testing datasets, the average decoding accuracies decreased by about 3% and 7%, respectively, compared to using 30° as testing dataset. At the same time, when the forearm angle of 45° was used as training dataset to test 30° and 75°, the decoding accuracies returned by the classification models were similar. It is confirmed that forearm angle had an impact on the accuracy of gesture decoding, and the greater the angle difference, the bigger the impact was. Moreover, a Pearson correlation analysis was performed on each subject to verify the universality of the influence of forearm angle on the model (
Table 4). It can be seen that almost all R values were greater than 0.7 except for subject 1 in 45 as validation dataset, confirming the universality of the impact of forearm angle.
4.3. Influence of Acquisition Time
Similar to
Section 4.2, the impact of acquisition time on gesture decoding was discussed in this section. In order to control the impact of muscle fatigue and forearm angle, only Class
datasets were used. Additionally, datasets with acquisition time of
were used to test the datasets of acquisition time of
respectively, with the same forearm angle (
Figure 11).
From the results in
Figure 11, it became clear that when using the same acquisition time data as both training and testing datasets, the accuracies of the two models were the highest, and the average decoding accuracies were close to 95%, which were similar to the results of forearm angle. Moreover, the bigger the gap of acquisition time was, the lower the decoding accuracy. For example, using
as training dataset,
as testing dataset, while using dataset
to test
, the average decoding accuracies both decreased by more than 20%. Nevertheless, models trained by
were used to test datasets
and
respectively, and average decoding accuracies decreased lower than the above models, by approximately 5–10%. Similarly, to the previous section, Pearson correlation coefficient was used to validate the universality of the conclusion (
Table 5). The majority of R values were rarely lower than 0.95. This is due to the fact that acquisition time had a considerable impact on gesture decoding (maximum above 20%), and the longer the collection time span, the more severe the impact. The Pearson correlation coefficient became insensitive in this instance, and tiny variations in the decoding accuracy of various participants will not induce changes in the correlation coefficient. Additionally, all subjects showed the same trend.
In summary, among factors such as muscle fatigue, forearm angle and acquisition time, the acquisition time had the greatest impact on the accuracy of gesture decoding, which may also be related to the position offset of the disposable electrode patch at different acquisition times.
4.4. Influence of MF, FA and AT
The three influencing factors (i.e., different muscle fatigue level, different forearm angle and different acquisition time) were included in each classification model. Therefore, 18 classification models were designed within three categories (
,
,
) for each subject (
Table 6).
For example, in
category, the data collected by
and
were used for training, and data acquired by
were used for testing. For the first model in
category, two of the five groups in A_b_30 and B_a_45 were randomly selected, respectively, to form training datasets and then choose one of five groups successively in C_a_75 as testing dataset, and the same procedures were followed for the other 17 models. To lower bias in the experimental results, the participants with the best and worst decoding performance were eliminated, and then, ten decoding result points were deducted from each of the three subjects in the center, for a total of 30 points in each model. The obtained results are shown in
Figure 12.
According to the results, the decoding accuracy rates of all major categories were not stable, with a maximum rate gap of more than 25%. Conversely, it was easy to find that the trend of decoding accuracies between and was similar, but the average accuracies of were higher than that of , nearly 5–10%. On the other hand, the trend of decoding accuracies of was stable, which was different from the other two categories. As a result, it is postulated that a major reason for this situation was the different acquisition time. Moreover, when choosing bigger gap of forearm angle data as training datasets (randomly choose two out of five groups in angle of 30° and 75°, respectively), the average decoding accuracies generally deteriorated.
5. Conclusions
In this paper, the effects of muscle fatigue, forearm angle and acquisition time on the validation accuracy of gesture decoding were investigated. For this purpose, four specific muscles (i.e., SFD, FCU, ECRL and FE) and 11 hand movements, commonly used in daily life, were selected. Meanwhile, four TD features (RMS, WL, ZC, and SSC) and two classification models (LDA and PNN) were chosen to analyze the sEMG signal.
The analysis of the signal was performed in four parts: The first part was an analysis of the influence of muscle fatigue on the accuracy of gesture decoding. The second and third parts were analyses of the influence of forearm angle and acquisition time on the accuracy of gesture decoding. The final part was a comprehensive analysis of the effect of the three elements mentioned above on gesture decoding accuracy.
From
Section 4.1, it was concluded that muscle fatigue had an impact on the classification model for gesture decoding, by decreasing the average accuracy by approximately 7%. Nevertheless, the validation accuracy exceeded 88%, which showed that the negative impact of muscle fatigue was relatively small (
Figure 9). Based on the results of
Section 4.2 and
Section 4.3, it can be concluded that when using same forearm angle or acquisition time data as both training and testing datasets, the decoding accuracies of the two models were the highest, both close to 95%. Furthermore, it was observed that the average test accuracy was deteriorating with the increasing gap of forearm angle and acquisition time. However, the negative impact on the accuracy of gesture decoding of acquisition time was substantially higher than that of forearm angle. The maximum accuracy decrease of acquisition time was more than 20%, whereas that of forearm angle was less than 10%. Finally, the impact of three influencing elements on the classification model was comprehensively considered. The results showed that the decoding accuracy of each category was not stable. Among them,
and
had a similar accuracy trend, and the average accuracies of
were higher than that of
, close to 5–10%. However, the trend of average decoding accuracies of
was relatively stable.
On the one hand, human hand movement is one of the most complex limb movements, with many factors that hinder gesture decoding. On the other hand, as a non-invasive signal connected to limb movement, sEMG has several advantages in an intuitive human–computer interface, including convenience, freedom of space and light constraints. Therefore, the study of sEMG-based gesture decoding opens new opportunities for future practical applications, such as prosthetic control and virtual reality.
Although this article has provided theoretical and experimental results, many issues that need further discussion still remain. First, the conditions for classifying muscle fatigue levels are only outlined, so a more precise and effective definition of the conditions for muscle fatigue classification is needed. Second, this paper only explored the EMG signals of the three angles of the forearm when the human body sits upright, which only covers a small part of the actual human movement. Therefore, more scenarios need to be explored. Third, this article only used the EMG data collected in three days. In the future, we will research the changes of EMG signal over time and the impact on the classification model of gesture decoding in a longer time span. Finally, the experiment described in this paper was carried out in a university laboratory, and the volunteers there were graduate students pursuing a master’s degree, so they were young and had little age difference. Furthermore, the problem of the left-hand or right-hand dominant was not considered in this research. In the following expansion experiment, volunteers of various ages and dominant hands will be recruited to carry out the experiment in order to ensure that the experimental outcomes are universal.