Comparison Study of Muscular-Contraction Classification Between Independent Component Analysis and Artificial Neural Network

Sueaseenak, Direk; Wibirama, Sunu; Chanwimalueang, Theerasak; Pintavirooj, C.; Sangworasil, Manas

doi:10.1109/iscit.2008.4700236

Cited by 7 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[81, p. 251]. This includes: -neural networks in different compositions [39], [93], [45], [47], [36], [8], [23], [42] [32], [4], [6], [90], [31], [30], [82], [86], including such based on adaptive resonance theory [91], -support vector machines and variants [49], [39], [48], [84], [66], [108], [90], [16], [86], -decision trees [30], -(naïve) Bayesian classification [103], [70], [52], [90], -fuzzy logic approaches [69], [3], -Gaussian mixture models [44], [106], [46], -logistic regression [30], -logistic model trees [30], -classification via independent component analysis (ICA) [93], canonical discriminant analysis [71], -linear discriminant analysis (LDA) [23], [22] [6], [31], [46], …”

Section: Related Workmentioning

confidence: 99%

“…The following features and transformations have proven well in the context of pattern-recognition-based myoelectric control (cf. [81, p. 250-251]): -linear envelope [107], [104, p. 271], [76], [10], -zero crossings and variance [87], -integral absolute value, variance, zero crossing [94], -mean absolute value [6], its slope, wave form length, number of waveform slope sign changes, number of waveform zero crossings (Hudgins set of features) [45], -frequency spectrum via Fourier transform [26], [39], [93], random Fourier features [35], [34], as well as local frequency and phase content via short-time Fourier transform [41], [23,22], [91], -autoregressive coefficients [103], [14], [55], -cepstral coefficients [103], [14], -wavelet decomposition coefficients [23,22], [47], [67], [36], [8], [48], [84] and their Eigenvalues [66], -wavelet packet feature sets [23,22], motor unit action potentials (MUAPs) via wavelet packet transform and fuzzy C-means clustering [85], -signal energy (overall, within Hamming windows, within trapezoidal windows) as temporal features and spectral magnitude as well as spectral moments from short-time Thompson transform [91], -moving approximate entropy [2], andcontraction factors from fractal modeling [55], fractal dimensions [...…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Prototype Reduction on sEMG Data for Instance-based Gesture Learning towards Real-time Prosthetic Control

Sziburis

Nowak

Brunelli

2021

Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies

View full text Add to dashboard Cite

This work presents the design, implementation and validation of learning techniques based on the kNN scheme for gesture detection in prosthetic control. To cope with high computational demands in instance-based prediction, methods of dataset reduction are evaluated considering real-time determinism to allow for the reliable integration into battery-powered portable devices.The influence of parameterization and varying proportionality schemes is analyzed, utilizing an eight-channel-sEMG armband. Besides offline cross-validation accuracy, success rates in real-time pilot experiments (online target achievement tests) are determined.Based on the assessment of specific dataset reduction techniques' adequacy for embedded control applications regarding accuracy and timing behaviour, Decision Surface Mapping (DSM) proves itself promising when applying kNN on the reduced set.A randomized, double-blind user study was conducted to evaluate the respective methods (kNN and kNN with DSM-reduction) against Ridge Regression (RR) and RR with Random Fourier Features (RR-RFF). The kNN-based methods performed significantly better (𝑝 < 0.0005) than the regression techniques. Between DSM-kNN and kNN, there was no statistically significant difference (significance level 0.05). This is remarkable in consideration of only one sample per class in the reduced set, thus yielding a reduction rate of over 99% while preserving success rate. The same behaviour could be confirmed in an extended user study.With 𝑘 = 1, which turned out to be an excellent choice, the runtime complexity of both kNN (in every prediction step) as well as DSM-kNN (in the training phase) becomes

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Prototype Reduction on sEMG Data for Instance-based Gesture Learning towards Real-time Prosthetic Control

Sziburis

Nowak

Brunelli

2021

Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies

View full text Add to dashboard Cite

show abstract

“…Several mathematical and Artificial Intelligence (AI) techniques have received extensive attraction for the analysis and classification of EMG signals. Among the most common classification methods are the Bayesian systems [5], artificial neural networks (ANN) [3,6], Markov maps [7], and fuzzy logic [4] [8].…”

Section: Introductionmentioning

confidence: 99%

A case study on tuning artificial neural networks to recognize signal patterns of hand motions

et al. 2015

View full text Add to dashboard Cite

This paper presents the development of artificial neural networks (ANN) as pattern recognition systems to classify surface electromyography signals (sEMG) into nine select hand motions from seven subjects. Multiple networks were designed to determine how well a network could adapt to signals from different subjects. This was achieved by developing multiple networks with different combinations of the volunteers for training. Each network was tested with signals from all volunteers to determine how well they could adapt to new subjects. It was found that ANNs trained using only one or two subjects would perform exceptionally well when tested with signals from the same subjects but relatively poorly when tested with signals from new subjects. As the number of subjects used for training increased, the ability of the network to accurately classify the signals from the trainees decreased but their ability to adapt to signals from new subjects increased. Solely based on these results, it can be inferred that ANNs developed using signals from a large amount of subjects could be used to accurately classify signals from completely new subjects. Research presented in this paper has potential to be further developed as a basis for utilizing sEMG as control signals in electric devices such as myoelectric prosthesis or humanoid control. Index Terms-sEMG signal classification, Artificial Neural Networks (ANN), human-machine interaction

show abstract

“…Even though radio Frequency Identification (RFID) tags can be used for this purpose, their major drawback is the transmission range. It is difficult to transmit information beyond distances of few kilometres, even with active RFID tags and passive tags allow transmission only up to a maximum of 500 m. Recently, Cypress ™ Programmable System on Chip (PSoC) gained much attention for acquisition and processing of biomedical signals [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Development of a secure body area network for a wearable physiological monitoring system using a PSoC processor

Sriraam¹,

Swathy²,

Vijayalakshmi³

2011

Journal of Medical Engineering & Technology

View full text Add to dashboard Cite

Wearable physiological monitoring systems have gained popularity in the recent years due to their ability to continuously monitor physiological signals, thereby making them suitable for home-healthcare applications. The electrocardiogram (ECG), phonocardiogram (PCG) and photoplethysmogram (PPG) signals have been studied and it has been observed that there is a correlation between the three signals. This paper proposes the development of a secure body area network (BAN), for a wearable physiological monitoring system. The BAN is composed of three nodes, for ECG, PPG and PCG signals. The peak-peak distances of these signals are calculated first, in the coordinator of BAN. The coordinator is designed in such a manner that signals from it are transmitted to a monitoring station, only if the difference between the peak-peak distances of both ECG-PPG signals and ECG-PCG signals fall below a threshold. The entire operation of the coordinator is implemented using a real-time processor, Cypress(™) Programmable System on Chip (PSoC).

show abstract

Comparison Study of Muscular-Contraction Classification Between Independent Component Analysis and Artificial Neural Network

Cited by 7 publications

References 17 publications

Prototype Reduction on sEMG Data for Instance-based Gesture Learning towards Real-time Prosthetic Control

Prototype Reduction on sEMG Data for Instance-based Gesture Learning towards Real-time Prosthetic Control

A case study on tuning artificial neural networks to recognize signal patterns of hand motions

Development of a secure body area network for a wearable physiological monitoring system using a PSoC processor

Contact Info

Product

Resources

About