1,721,285 research outputs found
On the use of fuzzy and permutation entropy in hand gesture characterization from EMG signals: Parameters selection and comparison
Full text linkThe surface electromyography signal (sEMG) is widely used for gesture characterization; its reliability is strongly connected to the features extracted from sEMG recordings. This study aimed to investigate the use of two complexity measures, i.e., fuzzy entropy (FEn) and permutation entropy (PEn) for hand gesture characterization. Fourteen upper limb movements, sorted into three sets, were collected on ten subjects and the performances of FEn and PEn for gesture descriptions were analyzed for different computational parameters. FEn and PEn were able to properly cluster the expected numbers of gestures, but computational parameters were crucial for ensuring clusters’ separability and proper gesture characterization. FEn and PEn were also compared with other eighteen classical time and frequency domain features through the minimum redundancy maximum relevance algorithm and showed the best predictive importance scores in two gesture sets; they also had scores within the subset of the best five features in the remaining one. Further, the classification accuracies of four different feature sets presented remarkable increases when FEn and PEn are included as additional features. Outcomes support the use of FEn and PEn for hand gesture description when computational parameters are properly selected, and they could be useful in supporting the development of robotic arms and prostheses myoelectric control
Long term correlation and inhomogeneity of the inverted pendulum sway time-series under the intermittent control paradigm
Full text linkIn this study the extended detrended fluctuation analysis (EDFA) was applied to the sway data generated from an inverted pendulum (IP) model, intermittently controlled at the ankle. The time series taken into account was the center of pressure (COP), since it represents the widest used time series in posturography, and it constitutes a natural link between model and data-based analysis approaches for studying the dynamics of the human balance maintenance. COP time-series were obtained by varying the intermittent control parameters (ICP) in a uniform distribution range that ensures IP stability to quantify changes in the long-term correlation and inhomogeneity of the time-series. Globally, EDFA coefficients (α and β) showed to be sensitive to the variations of derivative control gain (D), whereas for proportional gain (P) and ρ parameters no significant trends were observed. However, relations between EDFA coefficients and ρ arose whether derivative gain is examined within a low and high regions of value. For low D gains, both α and β showed a significant correlation with ρ, which disappears when higher D values were considered. Thus EDFA coefficients can provide useful insights about the long-term correlation and local characteristics of COP timeseries, which are strictly related to the control policy adopted for maintaining balance. This supports the validity of the intermittent motor control paradigm for the human upright stance and suggests the use of EDFA in real posturography applications, in order to extract meaningful information regarding the properties of COP timeseries for different groups of patients
On the Decoding of Shoulder Joint Intent of Motion from Transient EMG: Feature Evaluation and Classification
Full text linkMotion intent detection for shoulder actions may allow the early decoding of upper limb motions, thus enhancing the real-time usability of rehabilitative devices and prosthetics. In this study we faced a motion intent detection problem involving four shoulder movements by using transient epochs of surface electromyographic (EMG) signals. Reliability of time and frequency domain features was investigated through clusters separability properties and classification performances. Those features able to provide accuracy greater than 90% were selected and further investigated by a holdout scheme, i.e. decreasing the amount of data for training the learning models (60%, 50%, 40%, and 30%). Key findings of the study are as follows. Firstly, single-feature approach appeared suitable for early decoding shoulder movements, thus supporting reduced recording setup. Time domain features related to the instantaneous variations of signal amplitude produced the best results but frequency domain features showed comparable performances, suggesting no favored domain for feature extraction. Eventually, autoregressive coefficients suffered from a reduced amount of data used for training. Outcomes of this study can support the design of myoelectric control schemes, based on transient EMG data, for driving shoulder joint assistive devices
Improving EMG Signal Change Point Detection for Low SNR by Using Extended Teager-Kaiser Energy Operator
No full textMuscle onset detection plays a key role in applications ranging from clinical to assistive technology. The Teager-Kaiser energy operator (TKEO) is an acknowledged tool used in surface electromyography (sEMG) signal conditioning for improving the performances of many change-point detection methods. Here, a TKEO extended version (ETKEO) was used to investigate its effects, for different SNR ranges, among a series of well-assessed algorithms, including a threshold-based one (TP). An optimization procedure on synthetic signals for the selection of the operator structure was also developed. The detection errors between TKEO and ETKEO, performed on real sEMG signals with SNR≤8 dB, showed significant ( {p} < 0.05 ) overall improvements, not lower than 30%, when ETKEO was used. When compared with more robust techniques preconditioned by ETKEO as well, i.e., wavelet-, CUSUM- and profile likelihood maximization-based algorithms, the TP detector reached comparable performances for each SNR band, also for the lowest one. The results support the relevance of using ETKEO to improve onset analysis methods for a wide range of low SNR values, being particularly suitable for applications such as myoelectric motion intention detection. Moreover, the ETKEO adaptable structure suggests its use for other biological signals, presenting different characteristics with respect to sEMG signals
Can the Nintendo WII Balance Board be Used for a Reliable Assessment of the Initiation of Gait?
Full text linkThe Nintendo WII balance board (NWBB) is appreciated not only as a gaming device but also as an alternative to laboratory grade force plate in clinical and human motion research applications. Despite its validity during postural and quasi-static motor tasks has been evaluated in several studies, no hints were provided about its usability during gait initiation for the anticipatory postural adjustments analysis. In this study the validity of the NWBB was assessed by comparing temporal and spatial parameters from center of pressure trajectories with those obtained from a dynamometric force plate. The similarity between the trajectories was confirmed by the low values of root mean square error. The percentage errors in spatial parameters resulted under 10% for the whole trajectory and under 15% for the anterior/posterior and medial/lateral component respectively. Bland-Altman plots showed errors equally distributed around the mean difference, without a significant proportional tendency. Consistency and agreement between measures, verified by the high values of intra-class correlation coefficients, were further confirmed by temporal parameters characterized by limited errors, lower than 14%, for each gait initiation phases. Findings of the present study confirm the usability of the NWBB not only for static but also dynamic tasks and can contribute to enhance the use of such device for investigating the initiation of gait in clinical and not-specialized contexts
Center of pressure plausibility for the double-link human stance model under the intermittent control paradigm
Full text linkDespite human balance maintenance in quiet conditions could seem a trivial motor task, it is not. Recently, the human stance was described through a double link inverted pendulum (DIP) actively controlled at the ankle with an intermittent proportional (P) and derivative (D) control actions based on the sway of a virtual inverted pendulum (VIP) that links the ankle joint with the DIP center of mass. Such description, encompassing both the mechanical model and the intermittent control policy, was referred as the DIP/VIP human stance model, and it showed physiologically plausible kinematic patterns. In this study a mathematical formalization of the Center of pressure (COP) for a DIP structure was developed. Then, it was used in conjunction with an intermittently controlled DIP/VIP model to assess its kinetic plausibility. Three descriptors commonly employed in posturography were selected among six based on their capability to discriminate between young (Y) and elderly (O) adults groups. Then, they were applied to assess whether variations of the P–D parameters affect the synthetic COP. The results showed that DIP/VIP model can reproduce COP trajectories, showing characteristics similar to the Y and O groups. Moreover, it was observed that both P and D parameters increased passing from Y to O, indicating that the COP obtained from the DIP/VIP model is able to highlight differences in balance control between groups. The study hence promote the use of DIP/VIP in posturography, where inferential techniques can be applied to characterize neural control
Evaluation of physical effort by IoT-based wearable sensors
Full text linkAssessment of physical effort commonly addressed in research through acceleration signals can show significant measurement errors. The approach presented in this paper formulates a proper measurement system to evaluate the physical effort by wearable devices. Specifically, the paper proposes the joint use of sensors for skin conductance (SC) and electromyography (EMG). The EMG sensor is introduced uniquely with the aim of properly identifying the effort level. The classification is, instead, entirely entrusted to the SC signal alone. The proposed approach is then tested in the evaluation of muscular fatigue felt by arms. The experimental results show good performance, as the obtained values in terms of classification accuracy and sensitivity are, respectively, 84.68 % and 89.75 %
Identification of Neurodegenerative Diseases From Gait Rhythm Through Time Domain and Time-Dependent Spectral Descriptors
Full text linkThe analysis of gait rhythm by pattern recognition can support the state-of-the-art clinical methods for the identification of neurodegenerative diseases (NDD). In this study, we investigated the use of time domain (TD) and time-dependent spectral features (PSDTD) for detecting NDD sub-types. Also, we proposed two classification pathways for supporting NDD diagnosis, the first one made by a two-step learning phase, whereas the second one encompasses a single learning model. We considered stride-to-stride fluctuation data of healthy controls (CN), patients affected by Parkinson's disease (PD), Huntington's disease (HD), and amyotrophic lateral sclerosis (AS). TD feature set provided good results to distinguish between CN and NDDs, while performances lowered for specific NDD identification. PSDTD features boosted the accuracy of each binary identification task. With k-nearest neighbor classifier, the first diagnosis pathway reached 98.76% accuracy to distinguish between CN and NDD and 94.56% accuracy for NDDs sub-types, whereas the second pathway offered an overall accuracy of 94.84% for a 4-class classification task. Outcomes of this study indicate that the use of TD and PSDTD features, simple to extract and with a low computational load, provides reliable results in terms of NDD identification, being also useful for the development of gait rhythm computer-aided NDD detection systems
- …
