Walking Speed Classification from Marker-Free Video Images in Two-Dimension Using Optimum Data and a Deep Learning Method.

Walking speed is considered a reliable assessment tool for any movement-related functional activities of an individual (i.e., patients and healthy controls) by caregivers and clinicians. Traditional video surveillance gait monitoring in clinics and aged care homes may employ modern artificial intelligence techniques to utilize walking speed as a screening indicator of various physical outcomes or accidents in individuals. Specifically, ratio-based body measurements of walking individuals are extracted from marker-free and two-dimensional video images to create a walk pattern suitable for walking speed classification using deep learning based artificial intelligence techniques. However, the development of successful and highly predictive deep learning architecture depends on the optimal use of extracted data because redundant data may overburden the deep learning architecture and hinder the classification performance. The aim of this study was to investigate the optimal combination of ratio-based body measurements needed for presenting potential information to define and predict a walk pattern in terms of speed with high classification accuracy using a deep learning-based walking speed classification model. To this end, the performance of different combinations of five ratio-based body measurements was evaluated through a correlation analysis and a deep learning-based walking speed classification test. The results show that a combination of three ratio-based body measurements can potentially define and predict a walk pattern in terms of speed with classification accuracies greater than 92% using a bidirectional long short-term memory deep learning method.

A review on crosstalk in myographic signals.

PURPOSE: Crosstalk in myographic signals is a major hindrance to the understanding of local information related to individual muscle function. This review aims to analyse the problem of crosstalk in electromyography and mechanomyography. METHODS: An initial search of the SCOPUS database using an appropriate set of keywords yielded 290 studies, and 59 potential studies were selected after all the records were screened using the eligibility criteria. This review on crosstalk revealed that signal contamination due to crosstalk remains a major challenge in the application of surface myography techniques. Various methods have been employed in previous studies to identify, quantify and reduce crosstalk in surface myographic signals. RESULTS: Although correlation-based methods for crosstalk quantification are easy to use, there is a possibility that co-contraction could be interpreted as crosstalk. High-definition EMG has emerged as a new technique that has been successfully applied to reduce crosstalk. CONCLUSIONS: The phenomenon of crosstalk needs to be investigated carefully because it depends on many factors related to muscle task and physiology. This review article not only provides a good summary of the literature on crosstalk in myographic signals but also discusses new directions related to techniques for crosstalk identification, quantification and reduction. The review also provides insights into muscle-related issues that impact crosstalk in myographic signals.

Analysis of crosstalk in the mechanomyographic signals generated by forearm muscles during different wrist postures.

INTRODUCTION: In this study, we analyzed the crosstalk in mechanomyographic (MMG) signals generated by the extensor digitorum (ED), extensor carpi ulnaris (ECU), and flexor carpi ulnaris (FCU) muscles of the forearm during wrist flexion (WF) and extension (WE) and radial (RD) and ulnar (UD) deviations. METHODS: Twenty right-handed men (mean ± SD age=26.7 ± 3.83 years) performed the wrist postures. During each wrist posture, MMG signals were detected using 3 accelerometers. Peak cross-correlations were used to quantify crosstalk. RESULTS: The level of crosstalk ranged from 1.69 to 64.05%. The wrist postures except the RD did not influence the crosstalk significantly between muscle pairs. However, muscles of the forearm compartments influenced the level of crosstalk for each wrist posture significantly. CONCLUSIONS: The results may be used to improve our understanding of the mechanics of the forearm muscles during wrist postures.

EMG-force relationship during static contraction: Effects on sensor placement locations on biceps brachii muscle.

BACKGROUND: The relationship between surface electromyography (EMG) and force have been the subject of ongoing investigations and remain a subject of controversy. Even under static conditions, the relationships at different sensor placement locations in the biceps brachii (BB) muscle are complex. OBJECTIVE: The aim of this study was to compare the activity and relationship between surface EMG and static force from the BB muscle in terms of three sensor placement locations. METHODS: Twenty-one right hand dominant male subjects (age 25.3 ± 1.2 years) participated in the study. Surface EMG signals were detected from the subject's right BB muscle. The muscle activation during force was determined as the root mean square (RMS) electromyographic signal normalized to the peak RMS EMG signal of isometric contraction for 10 s. The statistical analysis included linear regression to examine the relationship between EMG amplitude and force of contraction [40-100% of maximal voluntary contraction (MVC)], repeated measures ANOVA to assess differences among the sensor placement locations, and coefficient of variation (CoV) for muscle activity variation. RESULTS: The results demonstrated that when the sensor was placed on the muscle belly, the linear slope coefficient was significantly greater for EMG versus force testing (r^{2} = 0.61, P > 0.05) than when placed on the lower part (r^{2}=0.31, P< 0.05) and upper part of the muscle belly (r^{2}=0.29, P > 0.05). In addition, the EMG signal activity on the muscle belly had less variability than the upper and lower parts (8.55% vs. 15.12% and 12.86%, respectively). CONCLUSION: These findings indicate the importance of applying the surface EMG sensor at the appropriate locations that follow muscle fiber orientation of the BB muscle during static contraction. As a result, EMG signals of three different placements may help to understand the difference in the amplitude of the signals due to placement.

Longitudinal, lateral and transverse axes of forearm muscles influence the crosstalk in the mechanomyographic signals during isometric wrist postures.

PROBLEM STATEMENT: In mechanomyography (MMG), crosstalk refers to the contamination of the signal from the muscle of interest by the signal from another muscle or muscle group that is in close proximity. PURPOSE: The aim of the present study was two-fold: i) to quantify the level of crosstalk in the mechanomyographic (MMG) signals from the longitudinal (Lo), lateral (La) and transverse (Tr) axes of the extensor digitorum (ED), extensor carpi ulnaris (ECU) and flexor carpi ulnaris (FCU) muscles during isometric wrist flexion (WF) and extension (WE), radial (RD) and ulnar (UD) deviations; and ii) to analyze whether the three-directional MMG signals influence the level of crosstalk between the muscle groups during these wrist postures. METHODS: Twenty, healthy right-handed men (mean ± SD: age = 26.7±3.83 y; height = 174.47±6.3 cm; mass = 72.79±14.36 kg) participated in this study. During each wrist posture, the MMG signals propagated through the axes of the muscles were detected using three separate tri-axial accelerometers. The x-axis, y-axis, and z-axis of the sensor were placed in the Lo, La, and Tr directions with respect to muscle fibers. The peak cross-correlations were used to quantify the proportion of crosstalk between the different muscle groups. RESULTS: The average level of crosstalk in the MMG signals generated by the muscle groups ranged from: 34.28-69.69% for the Lo axis, 27.32-52.55% for the La axis and 11.38-25.55% for the Tr axis for all participants and their wrist postures. The Tr axes between the muscle groups showed significantly smaller crosstalk values for all wrist postures [F (2, 38) = 14-63, p<0.05, η2 = 0.416-0.769]. SIGNIFICANCE: The results may be applied in the field of human movement research, especially for the examination of muscle mechanics during various types of the wrist postures.

EMG-force relationship during static contraction: effects on sensor placement locations on biceps brachii muscle.

BACKGROUND: The relationship between surface electromyography (EMG) and force have been the subject of ongoing investigations and remain a subject of controversy. Even under static conditions, the relationships at different sensor placement locations in the biceps brachii (BB) muscle are complex. OBJECTIVE: The aim of this study was to compare the activity and relationship between surface EMG and static force from the BB muscle in terms of three sensor placement locations. METHODS: Twenty-one right hand dominant male subjects (age 25.3±1.2 years) participated in the study. Surface EMG signals were detected from the subject's right BB muscle. The muscle activation during force was determined as the root mean square (RMS) electromyographic signal normalized to the peak RMS EMG signal of isometric contraction for 10 s. The statistical analysis included linear regression to examine the relationship between EMG amplitude and force of contraction [40-100% of maximal voluntary contraction (MVC)], repeated measures ANOVA to assess differences among the sensor placement locations, and coefficient of variation (CoV) for muscle activity variation. RESULTS: The results demonstrated that when the sensor was placed on the muscle belly, the linear slope coefficient was significantly greater for EMG versus force testing (r2=0.62, P<0.05) than when placed on the lower part (r2=0.31, P>0.05) and upper part of the muscle belly (r2=0.29, P<0.05). In addition, the EMG signal activity on the muscle belly had less variability than the upper and lower parts (8.55% vs. 15.12% and 12.86%, respectively). CONCLUSION: These findings indicate the importance of applying the surface EMG sensor at the appropriate locations that follow muscle fiber orientation of the BB muscle during static contraction. As a result, EMG signals of three different placements may help to understand the difference in the amplitude of the signals due to placement.

Evaluation of repetitive isometric contractions on the heads of triceps brachii muscle during grip force exercise.

OBJECTIVES: Normally, surface electromyography electrodes are used to evaluate the activity of superficial muscles during various kinds of voluntary contractions of muscle fiber. The objective of the present study was to investigate the effect of repetitive isometric contractions on the three heads of the triceps brachii muscle during handgrip force exercise. METHODS: Myoelectric signals were recorded from the lateral, long and medial heads of the triceps brachii muscle in 13 healthy males during maximal isometric contractions for 10 s of concurrent handgrip force and elbow extension. The subjects were asked to perform their contraction task five times with 3 minutes interval between two successive contractions. RESULTS: Decreasing electromyographic activities were found for the lateral and long heads, and increasing for the medial head throughout the 5 different contractions. Electromyographic activities were found for the lateral head with mean=199.84, SD=7.65, CV=3.83%, the long head with mean=456.76, SD=18.10, CV=3.96%, and the medial head with mean=505.16, SD=8.47, CV=1.68%. Electromyographic activities among the three heads of triceps brachii were significantly different (F=3.82) at the alpha level of (p<0.05). CONCLUSIONS: These findings support that repetitive isometric contractions decrease the contractile activity in the lateral and long heads, and increases in the medial head of the triceps brachii muscle during handgrip force exercise with full elbow extension, and the electromyographic activity changes are observed to be more significant at the long head as compared to the lateral and medial heads.

Cross-talk in mechanomyographic signals from the forearm muscles during sub-maximal to maximal isometric grip force.

PURPOSE: This study aimed: i) to examine the relationship between the magnitude of cross-talk in mechanomyographic (MMG) signals generated by the extensor digitorum (ED), extensor carpi ulnaris (ECU), and flexor carpi ulnaris (FCU) muscles with the sub-maximal to maximal isometric grip force, and with the anthropometric parameters of the forearm, and ii) to quantify the distribution of the cross-talk in the MMG signal to determine if it appears due to the signal component of intramuscular pressure waves produced by the muscle fibers geometrical changes or due to the limb tremor. METHODS: Twenty, right-handed healthy men (mean ± SD: age  = 26.7±3.83 y; height  = 174.47±6.3 cm; mass  = 72.79±14.36 kg) performed isometric muscle actions in 20% increment from 20% to 100% of the maximum voluntary isometric contraction (MVIC). During each muscle action, MMG signals generated by each muscle were detected using three separate accelerometers. The peak cross-correlations were used to quantify the cross-talk between two muscles. RESULTS: The magnitude of cross-talk in the MMG signals among the muscle groups ranged from, R2(x, y) = 2.45-62.28%. Linear regression analysis showed that the magnitude of cross-talk increased linearly (r2 = 0.857-0.90) with the levels of grip force for all the muscle groups. The amount of cross-talk showed weak positive and negative correlations (r2 = 0.016-0.216) with the circumference and length of the forearm respectively, between the muscles at 100% MVIC. The cross-talk values significantly differed among the MMG signals due to: limb tremor (MMGTF), slow firing motor unit fibers (MMGSF) and fast firing motor unit fibers (MMGFF) between the muscles at 100% MVIC (p<0.05, η2 = 0.47-0.80). SIGNIFICANCE: The results of this study may be used to improve our understanding of the mechanics of the forearm muscles during different levels of the grip force.

Hybrid markerless tracking of complex articulated motion in golf swings.

Sports video tracking is a research topic that has attained increasing attention due to its high commercial potential. A number of sports, including tennis, soccer, gymnastics, running, golf, badminton and cricket have been utilised to display the novel ideas in sports motion tracking. The main challenge associated with this research concerns the extraction of a highly complex articulated motion from a video scene. Our research focuses on the development of a markerless human motion tracking system that tracks the major body parts of an athlete straight from a sports broadcast video. We proposed a hybrid tracking method, which consists of a combination of three algorithms (pyramidal Lucas-Kanade optical flow (LK), normalised correlation-based template matching and background subtraction), to track the golfer's head, body, hands, shoulders, knees and feet during a full swing. We then match, track and map the results onto a 2D articulated human stick model to represent the pose of the golfer over time. Our work was tested using two video broadcasts of a golfer, and we obtained satisfactory results. The current outcomes of this research can play an important role in enhancing the performance of a golfer, provide vital information to sports medicine practitioners by providing technically sound guidance on movements and should assist to diminish the risk of golfing injuries.

Surface electromyographic analysis of the biceps brachii muscle of cricket bowlers during bowling.

Cricket bowling generates forces with torques on the upper limb muscles and makes the biceps brachii (BB) muscle vulnerable to overuse injury. The aim of this study was to investigate whether there are differences in the amplitude of the EMG signal of the BB muscle during fast and spin delivery, during the seven phases of both types of bowling and the kinesiological interpretation of the bowling arm for muscle contraction mechanisms during bowling. A group of 16 male amateur bowlers participated in this study, among them 8 fast bowlers (FB) and 8 spin bowlers (SB). The root mean square (EMGRMS), the average sEMG (EMGAVG), the maximum peak amplitude (EMGpeak), and the variability of the signal were calculated using the coefficient of variance (EMGCV) from the BB muscle of each bowler (FB and SB) during each bowling phase. The results demonstrate that, (i) the BB muscle is more active during FB than during SB, (ii) the point of ball release and follow-through generated higher signals than the other five movements during both bowling categories, (iii) the BB muscle variability is higher during SB compared with FB, (iv) four statistically significant differences (p<0.05) found between the bowling phases in fast bowling and three in spin bowling, and (v) several arm mechanics occurred for muscle contraction. There are possible clinical significances from the outcomes; like, recurring dynamic contractions on BB muscle can facilitate to clarify the maximum occurrence of shoulder pain as well as biceps tendonitis those are medically observed in professional cricket bowlers, and treatment methods with specific injury prevention programmes should focus on the different bowling phases with the maximum muscle effect. Finally, these considerations will be of particular importance in assessing different physical therapy on bowler's muscle which can improve the ball delivery performance and stability of cricket bowlers.

Effects of anthropometric variables and electrode placement on the SEMG activity of the biceps brachii muscle during submaximal isometric contraction in arm wrestling.

Surface electromyography (SEMG) has been widely used to analyze the biceps brachii (BB) muscle during voluntary contraction, and the effect of the interelectrode distance has been studied. However, the effect of anthropometric variations and the placement of electrodes on the BB activity during arm wrestling (i.e., during isometric contraction at a submaximal intensity) has seldom been investigated. In this study, the BB strength throughout this type of static contraction was evaluated. The SEMG signals were recorded from three locations on the BB: the muscle belly (M), near proximal (P), and distal tendon (L) regions. Twenty subjects who participated in the experiment were divided into five groups (A, B, C, D, and E). The average SEMG, root mean square, and variability of the signal were calculated using the coefficient of variance. The results indicated that the M region was more active and exhibited increased signal consistency (10.91%) compared with the other two regions (P: 24.47% and L: 19.13%). Significant differences were observed between the L and P regions and between the M and P regions (p<0.05); however, there were no differences between the M and L regions (p>0.05). The increase in the SEMG value in groups B and C was significant (p<0.05), whereas groups A, D, and E did not exhibit a significant increase (p>0.05). In addition, muscle size was the strongest predictor of strength compared with body weight and height. The results suggest that the M region displays considerable SEMG effects and signal reliability. Furthermore, the SEMG measurements were found to correlate strongly with the strength of the contractions and the muscle size, and not with weight and height.