Fuzzy entropy (FuzzyEn), a new measure of time series regularity, was proposed and applied to the characterization of surface electromyography (EMG) signals. Similar to the two existing related measures ApEn and SampEn, FuzzyEn is the negative natural logarithm of the conditional probability that two vectors similar for m points remain similar for the next m+1 points. Importing the concept of fuzzy sets, vectors' similarity is fuzzily defined in FuzzyEn on the basis of exponential function and their shapes. Besides possessing the good properties of SampEn superior to ApEn, FuzzyEn also succeeds in giving the entropy definition in the case of small parameters. Its performance on characterizing surface EMG signals, as well as independent, identically distributed (i.i.d.) random numbers and periodical sinusoidal signals, shows that FuzzyEn can more efficiently measure the regularity of time series. The method introduced here can also be applied to other noisy physiological signals with relatively short datasets.

Characterization of Surface EMG Signal Based on Fuzzy Entropy

Pharmacological inhibitors of cyclin-dependent kinases

In pattern recognition-based myoelectric control, high accuracy for multiple discriminated motions is presented in most of related literature. However, there is a gap between the classification accuracy and the usability of practical applications of myoelectric control, especially the effect of long-term usage. This paper proposes and investigates the behavior of fifty time-domain and frequency-domain features to classify ten upper limb motions using electromyographic data recorded during 21days. The most stable single feature and multiple feature sets are presented with the optimum configuration of myoelectric control, i.e. data segmentation and classifier. The result shows that sample entropy (SampEn) outperforms other features when compared using linear discriminant analysis (LDA), a robust classifier. The averaged test classification accuracy is 93.37%, when trained in only initial first day. It brings only 2.45% decrease compared with retraining schemes. Increasing number of features to four, which consists of SampEn, the fourth order cepstrum coefficients, root mean square and waveform length, increase the classification accuracy to 98.87%. The proposed techniques achieve to maintain the high accuracy without the retraining scheme. Additionally, this continuous classification allows the real-time operation.

http://iihm.imag.fr/publs/2014/ESWA-Draft.pdf

EMG feature evaluation for improving myoelectric pattern recognition robustness

The first edition (1981) of this comprehensive work weighed 25 lb and had 3300 pages. This entirely new third edition, published 14 years later, has grown to 45 lb and 4850 pages. This growth is not due to inflation but is the direct result of the information explosion. The multiplication of techniques for imaging and studying the bone and soft tissues has made choosing the best method for examination of the patient more difficult and, in an environment in which cost-effectiveness has become a byword, more important. An underlying principle of this work is to guide the physician in the choice of the technology to be employed to get essential information quickly and efficiently. Dr Resnick has called on a group of 40 contributors for special information, but he himself has played a major role in the writing and has been more than an editor, thereby ensuring a consistent and

Diagnosis of Bone and Joint Disorders

A review of analytical techniques for gait data. Part 1: fuzzy, statistical and fractal methods

Fractal analysis of surface EMG signals from the biceps

Devising techniques and instrumentation for early detection of knee arthritis and chondromalacia presents a challenge in the domain of biomedical engineering. The purpose of the present investigation was to characterize normal knees and knees affected by osteoarthritis, rheumatoid arthritis, and chondromalacia using a set of noninvasive acceleration measurements. Ultraminiature accelerometers were placed on the skin over the patella in four groups of subjects, and acceleration measurements were obtained during leg rotation. Acceleration measurements were significantly different in the four groups of subjects in the time and frequency domains. Power spectral analysis revealed that the average power was significantly different for these groups over a 100–500 Hz range. Noninvasive acceleration measurements can characterize the normal, arthritis, and chondromalacia knees. However, a study on a larger group of subjects is indicated.

Noninvasive acceleration measurements to characterize knee arthritis and chondromalacia

Identification and classification of the dysphagic patient at risk of aspiration is important from a clinical point of view. Recently, we have developed techniques to quantify various biomechanical parameters that characterize the dysphagic patient, and have developed an expert system to classify patients based on these measurements. The purpose of the present investigation was to develop a fuzzy logic diagnosis system for classification of the patient with pharyngeal dysphagia into four categories of risk for aspiration. Non-invasive acceleration and swallow pressure measurements were obtained and five parameters were extracted from these measurements. A set of membership functions were defined for each parameter. The measured parameter values were fuzzified and fed to a rule base which provided a set of output membership values corresponding to each of the categories. The set of output values were defuzzified to obtain a continuous measure of classification. The fuzzy system was evaluated using the data obtained from 22 subjects. There was a complete agreement between the fuzzy system classification and the clinician's classification in 18 of the 22 patients. The fuzzy system overestimated the risk by half a category in two patients and underestimated by half a category in two patients. The fuzzy logic diagnosis system, together with the biomechanical measures, provides a tool for continued patient assessment on a daily basis to identify the patient who needs further videofluorography examination.

A fuzzy logic diagnosis system for classification of pharyngeal dysphagia

Position tracking and control using bioelectric signals are emerging as promising techniques. Surface electromyographic EMG signals are being researched for tracking human movements, direct proportional control of teleoperators, and object manipulation in VR environments. This study investigates the use of surface EMG to track elbow joint angle during flexion-extension of the arm applied to control of a virtual environment or an anthropomorphic telemanipulator. An intelligent system based on neural networks and fuzzy logic has been developed to use the processed surface EMG signal and predict the joint angle. The intelligent system has been tested on normal subjects performing flexion-extension of the arm of various angles and at several speeds. The joint angles predicted by the intelligent system were input to a computer-simulated model of an elbow manipulator. Preliminary results show the average root mean squared RMS error between the actual elbow joint angle measured with a goniometer and the joint angle reproduced by the robot model to be less than 20%. The technique of using EMG as an interface for tracking and direct biocontrol has great potential in VR and telemanipulation.

Emg-based interface for position tracking and control in vr environments and teleoperation

A set of neural networks was developed for EMG based control of telemanipulators. The neural network system provides an estimate of the joint angle at the elbow using surface EMG of biceps in real time. The joint angle was measured by a goniometer to calibrate the system and train the networks. Preliminary results during testing indicate an error of less than 20% between the joint angle estimate of the network and the actual joint angle.

http://ieeexplore.ieee.org/iel3/4363/12495/00575381.pdf

Srikanth Suryanarayanan

Papers

Fractal analysis of surface EMG signals from the biceps

Noninvasive acceleration measurements to characterize knee arthritis and chondromalacia

A fuzzy logic diagnosis system for classification of pharyngeal dysphagia

Emg-based interface for position tracking and control in vr environments and teleoperation

Artificial neural networks for estimation of joint angle from EMG signals