A Cross-Day Analysis of EMG Features, Classifiers, and Regressors for Swallowing Events Detection and Fluid Intake Volume Estimation.

Dehydration is a common problem among older adults. It can seriously affect their health and wellbeing and sometimes leads to death, given the diminution of thirst sensation as we age. It is, therefore, essential to keep older adults properly hydrated by monitoring their fluid intake and estimating how much they drink. This paper aims to investigate the effect of surface electromyography (sEMG) features on the detection of drinking events and estimation of the amount of water swallowed per sip. Eleven individuals took part in the study, with data collected over two days. We investigated the best combination of a pool of twenty-six time and frequency domain sEMG features using five classifiers and seven regressors. Results revealed an average F-score over two days of 77.5±1.35% in distinguishing the drinking events from non-drinking events using three global features and 85.5±1.00% using three subject-specific features. The average volume estimation RMSE was 6.83±0.14 mL using one single global feature and 6.34±0.12 mL using a single subject-specific feature. These promising results validate and encourage the potential use of sEMG as an essential factor for monitoring and estimating the amount of fluid intake.

Vision-Based Methods for Food and Fluid Intake Monitoring: A Literature Review.

Food and fluid intake monitoring are essential for reducing the risk of dehydration, malnutrition, and obesity. The existing research has been preponderantly focused on dietary monitoring, while fluid intake monitoring, on the other hand, is often neglected. Food and fluid intake monitoring can be based on wearable sensors, environmental sensors, smart containers, and the collaborative use of multiple sensors. Vision-based intake monitoring methods have been widely exploited with the development of visual devices and computer vision algorithms. Vision-based methods provide non-intrusive solutions for monitoring. They have shown promising performance in food/beverage recognition and segmentation, human intake action detection and classification, and food volume/fluid amount estimation. However, occlusion, privacy, computational efficiency, and practicality pose significant challenges. This paper reviews the existing work (253 articles) on vision-based intake (food and fluid) monitoring methods to assess the size and scope of the available literature and identify the current challenges and research gaps. This paper uses tables and graphs to depict the patterns of device selection, viewing angle, tasks, algorithms, experimental settings, and performance of the existing monitoring systems.

Surface EMG Statistical and Performance Analysis of Targeted-Muscle-Reinnervated (TMR) Transhumeral Prosthesis Users in Home and Laboratory Settings.

A pattern-recognition (PR)-based myoelectric control system is the trend of future prostheses development. Compared with conventional prosthetic control systems, PR-based control systems provide high dexterity, with many studies achieving >95% accuracy in the last two decades. However, most research studies have been conducted in the laboratory. There is limited research investigating how EMG signals are acquired when users operate PR-based systems in their home and community environments. This study compares the statistical properties of surface electromyography (sEMG) signals used to calibrate prostheses and quantifies the quality of calibration sEMG data through separability indices, repeatability indices, and correlation coefficients in home and laboratory settings. The results demonstrate no significant differences in classification performance between home and laboratory environments in within-calibration classification error (home: 6.33 ± 2.13%, laboratory: 7.57 ± 3.44%). However, between-calibration classification errors (home: 40.61 ± 9.19%, laboratory: 44.98 ± 12.15%) were statistically different. Furthermore, the difference in all statistical properties of sEMG signals is significant (p < 0.05). Separability indices reveal that motion classes are more diverse in the home setting. In summary, differences in sEMG signals generated between home and laboratory only affect between-calibration performance.

On the Applications of EMG Sensors and Signals.

The ability to execute limb motions derives from composite command signals (or efferent signals) that stem from the central nervous system through the highway of the spinal cord and peripheral nerves to the muscles that drive the joints [...].

The Effect of EMG Features on the Classification of Swallowing Events and the Estimation of Fluid Intake Volume.

Nowadays, society is experiencing an increase in the number of adults aged 65 and over, and it is projected that the older adult population will triple in the coming decades. As older adults are prone to becoming dehydrated, which can significantly impact healthcare costs and staff, it is necessary to advance healthcare technologies to cater to such needs. However, there has not been an extensive research effort to implement a device that can autonomously track fluid intake. In particular, the ability of surface electromyographic sensors (sEMG) to monitor fluid intake has not been investigated in depth. Our previous study demonstrated a reasonable classification and estimation ability of sEMG using four features. This study aimed to examine if classification and estimation could be potentiated by combining an optimal subset of features from a library of forty-six time and frequency-domain features extracted from the data recorded using eleven subjects. Results demonstrated a classification accuracy of 95.94 ± 2.76% and an f-score of 94.93 ± 3.51% in differentiating between liquid swallows from non-liquid swallowing events using five features only, and a volume estimation RMSE of 2.80 ± 1.22 mL per sip and an average estimation error of 15.43 ± 8.64% using two features only. These results are encouraging and prove that sEMG could be a potential candidate for monitoring fluid intake.

Affordable Embroidered EMG Electrodes for Myoelectric Control of Prostheses: A Pilot Study.

Commercial myoelectric prostheses are costly to purchase and maintain, making their provision challenging for developing countries. Recent research indicates that embroidered EMG electrodes may provide a more affordable alternative to the sensors used in current prostheses. This pilot study investigates the usability of such electrodes for myoelectric control by comparing online and offline performance against conventional gel electrodes. Offline performance is evaluated through the classification of nine different hand and wrist gestures. Online performance is assessed with a crossover two-degree-of-freedom real-time experiment using Fitts' Law. Two performance metrics (Throughput and Completion Rate) are used to quantify usability. The mean classification accuracy of the nine gestures is approximately 98% for subject-specific models trained on both gel and embroidered electrode offline data from individual subjects, and 97% and 96% for general models trained on gel and embroidered offline data, respectively, from all subjects. Throughput (0.3 bits/s) and completion rate (95-97%) are similar in the online test. Results indicate that embroidered electrodes can achieve similar performance to gel electrodes paving the way for low-cost myoelectric prostheses.

Multiple-day high-dose beetroot juice supplementation does not improve pulmonary or muscle deoxygenation kinetics of well-trained cyclists in normoxia and hypoxia.

Dietary nitrate (NO3-) supplementation via beetroot juice (BR) has been reported to lower oxygen cost (i.e., increased exercise efficiency) and speed up oxygen uptake (VO2) kinetics in untrained and moderately trained individuals, particularly during conditions of low oxygen availability (i.e., hypoxia). However, the effects of multiple-day, high dose (12.4 mmol NO3- per day) BR supplementation on exercise efficiency and VO2 kinetics during normoxia and hypoxia in well-trained individuals are not resolved. In a double-blinded, randomized crossover study, 12 well-trained cyclists (66.4 ± 5.3 ml min-1∙kg-1) completed three transitions from rest to moderate-intensity (~70% of gas exchange threshold) cycling in hypoxia and normoxia with supplementation of BR or nitrate-depleted BR as placebo. Continuous measures of VO2 and muscle (vastus lateralis) deoxygenation (ΔHHb, using near-infrared spectroscopy) were acquired during all transitions. Kinetics of VO2 and deoxygenation (ΔHHb) were modeled using mono-exponential functions. Our results showed that BR supplementation did not alter the primary time constant for VO2 or ΔHHb during the transition from rest to moderate-intensity cycling. While BR supplementation lowered the amplitude of the VO2 response (2.1%, p = 0.038), BR did not alter steady state VO2 derived from the fit (p = 0.258), raw VO2 data (p = 0.231), moderate intensity exercise efficiency (p = 0.333) nor steady state ΔHHb (p = 0.224). Altogether, these results demonstrate that multiple-day, high-dose BR supplementation does not alter exercise efficiency or oxygen uptake kinetics during normoxia and hypoxia in well-trained athletes.

Modulation of SI and ACC response to noxious and non-noxious electrical stimuli after the spared nerve injury model of neuropathic pain.

BACKGROUND: The current knowledge on the role of SI and ACC in acute pain processing and how these contribute to the development of chronic pain is limited. Our objective was to investigate differences in and modulation of intracortical responses from SI and ACC in response to different intensities of peripheral presumed noxious and non-noxious stimuli in the acute time frame of a peripheral nerve injury in rats. METHODS: We applied non-noxious and noxious electrical stimulation pulses through a cuff electrode placed around the sciatic nerve and measured the cortical responses (six electrodes in each cortical area) before and after the spared nerve injury model. RESULTS: We found that the peak response correlated with the stimulation intensity and that SI and ACC differed in both amplitude and latency of cortical response. The cortical response to both noxious and non-noxious stimulation showed a trend towards faster processing of non-noxious stimuli in ACC and increased cortical processing of non-noxious stimuli in SI after SNI. CONCLUSIONS: We found different responses in SI and ACC to different intensity electrical stimulations based on two features and changes in these features following peripheral nerve injury. We believe that these features may be able to assist to track cortical changes during the chronification of pain in future animal studies. SIGNIFICANCE: This study showed distinct cortical processing of noxious and non-noxious peripheral stimuli in SI and ACC. The processing latency in ACC and accumulated spiking activity in SI appeared to be modulated by peripheral nerve injury, which elaborated on the function of these two areas in the processing of nociception.

Nerve Injury Decreases Hyperacute Resting-State Connectivity Between the Anterior Cingulate and Primary Somatosensory Cortex in Anesthetized Rats.

A better understanding of neural pain processing and of the development of pain over time, is critical to identify objective measures of pain and to evaluate the effect of pain alleviation therapies. One issue is, that the brain areas known to be related to pain processing are not exclusively responding to painful stimuli, and the neuronal activity is also influenced by other brain areas. Functional connectivity reflects synchrony or covariation of activation between groups of neurons. Previous studies found changes in connectivity days or weeks after pain induction. However, less in known on the temporal development of pain. Our objective was therefore to investigate the interaction between the anterior cingulate cortex (ACC) and primary somatosensory cortex (SI) in the hyperacute (minute) and sustained (hours) response in an animal model of neuropathic pain. Intra-cortical local field potentials (LFP) were recorded in 18 rats. In 10 rats the spared nerve injury model was used as an intervention. The intra-cortical activity was recorded before, immediately after, and three hours after the intervention. The interaction was quantified as the calculated correlation and coherence. The results from the intervention group showed a decrease in correlation between ACC and SI activity, which was most pronounced in the hyperacute phase but a longer time frame may be required for plastic changes to occur. This indicated that both SI and ACC are involved in hyperacute pain processing.

Chronic high-dose beetroot juice supplementation improves time trial performance of well-trained cyclists in normoxia and hypoxia.

Dietary nitrate (NO3-) supplementation via beetroot juice (BR) is known to improve endurance performance in untrained and moderately trained individuals. However, conflicting results exist in well-trained individuals. Evidence suggests that the effects of NO3- are augmented during conditions of reduced oxygen availability (e.g., hypoxia), thereby increasing the probability of performance improvements for well-trained athletes in hypoxia vs. normoxia. This randomized, double-blinded, counterbalanced-crossover study examined the effects of 7 days of BR supplementation with 12.4 mmol NO3- per day on 10-km cycling time trial (TT) performance in 12 well-trained cyclists in normoxia (N) and normobaric hypoxia (H). Linear mixed models for repeated measures revealed increases in plasma NO3- and NO2- after supplementation with BR (both p < 0.001). Further, TT performance increased with BR supplementation (∼1.6%, p < 0.05), with no difference between normoxia and hypoxia (p = 0.92). For respiratory variables there were significant effects of supplementation on VO2 (p < 0.05) and VE (p < 0.05) such that average VO2 and VE during the TT increased with BR, with no difference between normoxia and hypoxia (p ≥ 0.86). We found no effect of supplementation on heart rate, oxygen saturation or muscle oxygenation during the TT. Our results provide new evidence that chronic high-dose NO3- supplementation improves cycling performance of well-trained cyclists in both normoxia and hypoxia.

Distinct patterns of variation in the distribution of knee pain.

The patient's expression of pain using digital-body maps expands analytic opportunities for exploring the spatial variation of bodily pain. A common knee pain condition in adolescents and adults is patellofemoral pain (PFP) and recently PFP was shown to be characterized by a heterogeneous distribution of pain. Whether there are important patterns in these distributions remains unclear. This pioneering study assesses the spatial variation of pain using principal component analysis and a clustering approach. Detailed digital-body maps of knee pain were drawn by 299 PFP patients of mixed sex, age, and pain severity. Three pain distribution patterns emerged resembling an Anchor, Hook, and an Ovate shape on and around the patella. The variations in pain distribution were independent of sex, age, and pain intensity. Bilateral pain associated with a longer duration of pain and the majority characterized by the Hook and Ovate pain distributions. Bilateral and/or symmetrical pain between the left and right knees may represent symptoms associated with longstanding PFP. The distinct patterns of pain location and area suggest specific underlying structures cannot be ruled out as important drivers, although central neuronal mechanisms possibly exemplified by the symmetrical representation of pain may play a role in individuals with longstanding symptoms.

Online mapping of EMG signals into kinematics by autoencoding.

BACKGROUND: In this paper, we propose a nonlinear minimally supervised method based on autoencoding (AEN) of EMG for myocontrol. The proposed method was tested against the state-of-the-art (SOA) control scheme using a Fitts' law approach. METHODS: Seven able-bodied subjects performed a series of target acquisition myoelectric control tasks using the AEN and SOA algorithms for controlling two degrees-of-freedom (radial/ulnar deviation and flexion/extension of the wrist), and their online performance was characterized by six metrics. RESULTS: Both methods allowed a completion rate close to 100%, however AEN outperformed SOA for all other performance metrics, e.g. it allowed to perform the tasks on average in half the time with respect to SOA. Moreover, the amount of information transferred by the proposed method in bit/s was nearly twice the throughput of SOA. CONCLUSIONS: These results show that autoencoders can map EMG signals into kinematics with the potential of providing intuitive and dexterous control of artificial limbs for amputees.

Simulation of a Real-Time Brain Computer Interface for Detecting a Self-Paced Hitting Task.

OBJECTIVES: An invasive brain-computer interface (BCI) is a promising neurorehabilitation device for severely disabled patients. Although some systems have been shown to work well in restricted laboratory settings, their utility must be tested in less controlled, real-time environments. Our objective was to investigate whether a specific motor task could be reliably detected from multiunit intracortical signals from freely moving animals in a simulated, real-time setting. MATERIALS AND METHODS: Intracortical signals were first obtained from electrodes placed in the primary motor cortex of four rats that were trained to hit a retractable paddle (defined as a "Hit"). In the simulated real-time setting, the signal-to-noise-ratio was first increased by wavelet denoising. Action potentials were detected, and features were extracted (spike count, mean absolute values, entropy, and combination of these features) within pre-defined time windows (200 ms, 300 ms, and 400 ms) to classify the occurrence of a "Hit." RESULTS: We found higher detection accuracy of a "Hit" (73.1%, 73.4%, and 67.9% for the three window sizes, respectively) when the decision was made based on a combination of features rather than on a single feature. However, the duration of the window length was not statistically significant (p = 0.5). CONCLUSION: Our results showed the feasibility of detecting a motor task in real time in a less restricted environment compared to environments commonly applied within invasive BCI research, and they showed the feasibility of using information extracted from multiunit recordings, thereby avoiding the time-consuming and complex task of extracting and sorting single units.

Short-latency crossed responses in the human biceps femoris muscle.

KEY POINTS: The present study is the first to show short-latency crossed-spinal reflexes in the human upper leg muscles following mechanical rotations to the ipsilateral knee (iKnee) joint. The short-latency reflex in the contralateral biceps femoris (cBF) was inhibitory following iKnee extension perturbations, and facilitatory following iKnee flexion perturbations. The onset latency was 44 ms, indicating that purely spinal pathways mediate the cBF reflexes. The short-latency cBF inhibitory and facilitatory reflexes followed the automatic gain control principle, becoming larger as the level of background contraction in the cBF increased. The short-latency cBF reflexes were observed at the motor unit level using i.m. electromyography recordings, and the same population of cBF motor units that was inhibited following iKnee extensions was facilitated following iKnee flexions. Parallel interneuronal pathways from ipsilateral afferents to common motoneurons in the contralateral leg can therefore probably explain the perturbation direction-dependent reversal in the sign of the short-latency cBF reflex. ABSTRACT: Interlimb reflexes contribute to the central neural co-ordination between different limbs in both humans and animals. Although commissural interneurons have only been directly identified in animals, spinally-mediated interlimb reflexes have been discovered in a number of human lower limb muscles, indicating their existence in humans. The present study aimed to investigate whether short-latency crossed-spinal reflexes are present in the contralateral biceps femoris (cBF) muscle following ipsilateral knee (iKnee) joint rotations during a sitting task, where participants maintained a slight pre-contraction in the cBF. Following iKnee extension joint rotations, an inhibitory reflex was observed in the surface electromyographic (EMG) activity of the cBF, whereas a facilitatory reflex was observed in the cBF following iKnee flexion joint rotations. The onset latency of both cBF reflexes was 44 ms, which is too fast for a transcortical pathway to contribute. The cBF inhibitory and facilitatory reflexes followed the automatic gain control principle, with the size of the response increasing as the level of background pre-contraction in the cBF muscle increased. In addition to the surface EMG, both short-latency inhibitory and facilitatory cBF reflexes were recorded directly at the motor unit level by i.m. EMG, and the same population of cBF motor units that were inhibited following iKnee extension joint rotations were facilitated following iKnee flexion joint rotations. Therefore, parallel interneuronal pathways (probably involving commissural interneurons) from ipsilateral afferents to common motoneurons in the contralateral leg can probably explain the perturbation direction-dependent reversal in the sign of the short-latency cBF reflex.

Phantom movements from physiologically inappropriate muscles: A case study with a high transhumeral amputee.

Individuals with high-level amputation have a great need for functional prostheses because of their vast functional deficits. Conventional techniques are considered inappropriate for high-level amputees due to the lack of physiologically appropriate muscles. This study investigates how accurate phantom movements (PMs) can be classified from physiologically inappropriate muscles. The study involves a case study of a 42-year-old transhumeral amputee. Suitable PMs and best electrode configuration were identified using the sequential forward selection method and brute-force technique. Using linear discriminant analysis, the best PMs (elbow extension/flexion, wrist supination/pronation) and rest were classified with error ranging from 3% to 0.18% when using 3 to 8 EMG channels respectively. A completion rate of 93 % was obtained during a targeted achievement control test in a virtual reality environment. This case indicates that a proximal transhumeral amputee can generate muscle activation patterns related to distinct PMs; and these PMs can be decoded from physiologically inappropriate muscles.

Adaptation of local muscle blood flow and surface electromyography to repeated bouts of eccentric exercise.

The aim of this randomized controlled crossover study was to investigate the effect of a bout of unaccustomed eccentric exercise (ECC) followed by a consecutive bout of the same intensity on local muscle blood flow, amplitude, and frequency of the electromyographic (EMG) signal from the exercised tibialis anterior muscle. Sixteen healthy male participants (age, 25.7 (0.6) years; body mass index 24.8 (1) kg·m(-2) participated in this study. Two identical bouts of high-intensity ECC were performed on the tibialis anterior muscle 7 days apart. Control sessions involving no exercise were performed 4 weeks either before or after the exercise sessions. Changes in local total blood flow [ΔtHb], EMG root mean square, and median power frequency were recorded during isometric maximum voluntary contraction of ankle dorsiflexion. Measurements were performed before, immediately after, and the day after both ECCs (ECC1 and ECC2). The participants rested quietly in a chair in the control session. Eccentric exercise 1 led to a significant decrease in [ΔtHb] on the day after (p ≤ 0.05), whereas ECC2 did not. Median power frequency decreased significantly in ECC2 compared with ECC1 (p < 0.01). Root mean square was unchanged in all the instants. The present study showed that adaptation is depicted in the local muscle blood flow and the frequency contents of the EMG after an unaccustomed ECC inducing muscle soreness. These alterations provide a potential mechanism for a rapid adaptation, which decreases susceptibility of the muscle to develop further soreness in the subsequent ECC bout.

On the usability of intramuscular EMG for prosthetic control: a Fitts' Law approach.

Previous studies on intramuscular EMG based control used offline data analysis. The current study investigates the usability of intramuscular EMG in two degree-of-freedom using a Fitts' Law approach by combining classification and proportional control to perform a task, with real time feedback of user performance. Nine able-bodied subjects participated in the study. Intramuscular and surface EMG signals were recorded concurrently from the right forearm. Five performance metrics (Throughput,Path efficiency, Average Speed, Overshoot and Completion Rate) were used for quantification of usability. Intramuscular EMG based control performed significantly better than surface EMG for Path Efficiency (80.5±2.4% vs. 71.5±3.8%, P=0.004) and Overshoot (22.0±3.0% vs. 45.1±6.6%, P=0.01). No difference was found between Throughput and Completion Rate. However the Average Speed was significantly higher for surface (51.8±5.5%) than for intramuscular EMG (35.7±2.7%). The results obtained in this study imply that intramuscular EMG has great potential as control source for advanced myoelectric prosthetic devices.

Support vector regression for improved real-time, simultaneous myoelectric control.

This study describes the first application of a support vector machine (SVM) based scheme for real-time simultaneous and proportional myoelectric control of multiple degrees of freedom (DOFs). Three DOFs including wrist flexion-extension, abduction-adduction and forearm pronation-supination were investigated with 10 able-bodied subjects and two individuals with transradial limb deficiency (LD). A Fitts' law test involving real-time target acquisition tasks was conducted to compare the usability of the SVM-based control system to that of an artificial neural network (ANN) based method. Performance was assessed using the Fitts' law throughput value as well as additional metrics including completion rate, path efficiency and overshoot. The SVM-based approach outperformed the ANN-based system in every performance measure for able-bodied subjects. The SVM outperformed the ANN in path efficiency and throughput with the first LD subject and in throughput with the second LD subject. The superior performance of the SVM-based system appears to be due to its higher estimation accuracy of all DOFs during inactive and low amplitude segments (these periods were frequent during real-time control). Another advantage of the SVM-based method was that it substantially reduced the processing time for both training and real time control.

Identification of a self-paced hitting task in freely moving rats based on adaptive spike detection from multi-unit M1 cortical signals.

Invasive brain-computer interfaces (BCIs) may prove to be a useful rehabilitation tool for severely disabled patients. Although some systems have shown to work well in restricted laboratory settings, their usefulness must be tested in less controlled environments. Our objective was to investigate if a specific motor task could reliably be detected from multi-unit intra-cortical signals from freely moving animals. Four rats were trained to hit a retractable paddle (defined as a "hit"). Intra-cortical signals were obtained from electrodes placed in the primary motor cortex. First, the signal-to-noise ratio was increased by wavelet denoising. Action potentials were then detected using an adaptive threshold, counted in three consecutive time intervals and were used as features to classify either a "hit" or a "no-hit" (defined as an interval between two "hits"). We found that a "hit" could be detected with an accuracy of 75 ± 6% when wavelet denoising was applied whereas the accuracy dropped to 62 ± 5% without prior denoising. We compared our approach with the common daily practice in BCI that consists of using a fixed, manually selected threshold for spike detection without denoising. The results showed the feasibility of detecting a motor task in a less restricted environment than commonly applied within invasive BCI research.

Wrist torque estimation during simultaneous and continuously changing movements: surface vs. untargeted intramuscular EMG.

In this paper, the predictive capability of surface and untargeted intramuscular electromyography (EMG) was compared with respect to wrist-joint torque to quantify which type of measurement better represents joint torque during multiple degrees-of-freedom (DoF) movements for possible application in prosthetic control. Ten able-bodied subjects participated in the study. Surface and intramuscular EMG was recorded concurrently from the right forearm. The subjects were instructed to track continuous contraction profiles using single and combined DoF in two trials. The association between torque and EMG was assessed using an artificial neural network. Results showed a significant difference between the two types of EMG (P < 0.007) for all performance metrics: coefficient of determination (R(2)), Pearson correlation coefficient (PCC), and root mean square error (RMSE). The performance of surface EMG (R(2) = 0.93 ± 0.03; PCC = 0.98 ± 0.01; RMSE = 8.7 ± 2.1%) was found to be superior compared with intramuscular EMG (R(2) = 0.80 ± 0.07; PCC = 0.93 ± 0.03; RMSE = 14.5 ± 2.9%). The higher values of PCC compared with R(2) indicate that both methods are able to track the torque profile well but have some trouble (particularly intramuscular EMG) in estimating the exact amplitude. The possible cause for the difference, thus the low performance of intramuscular EMG, may be attributed to the very high selectivity of the recordings used in this study.