scholarly journals Analysis of EMG Signals in Aggressive and Normal Activities by Using Higher-Order Spectra

2012 ◽  
Vol 2012 ◽  
pp. 1-5 ◽  
Author(s):  
Necmettin Sezgin
Keyword(s):  
Electrical Potential ◽  
Higher Order ◽  
Electrical Potential Difference ◽  
Phase Coupling ◽  
Classification Result ◽  
Learning Machines ◽  
Emg Signal ◽  
Quadratic Phase ◽  
Higher Order Spectra

The analysis and classification of electromyography (EMG) signals are very important in order to detect some symptoms of diseases, prosthetic arm/leg control, and so on. In this study, an EMG signal was analyzed using bispectrum, which belongs to a family of higher-order spectra. An EMG signal is the electrical potential difference of muscle cells. The EMG signals used in the present study are aggressive or normal actions. The EMG dataset was obtained from the machine learning repository. First, the aggressive and normal EMG activities were analyzed using bispectrum and the quadratic phase coupling of each EMG episode was determined. Next, the features of the analyzed EMG signals were fed into learning machines to separate the aggressive and normal actions. The best classification result was 99.75%, which is sufficient to significantly classify the aggressive and normal actions.

Identification of freeplay and aerodynamic nonlinearities in a 2D aerofoil system with via higher-order spectra

2017 ◽  
Vol 121 (1244) ◽  
pp. 1530-1560 ◽  
Author(s):  
M. Candon ◽  
R. Carrese ◽  
H. Ogawa ◽  
P. Marzocca
Keyword(s):  
Pressure Coefficient ◽  
High Amplitude ◽  
Higher Order ◽  
Limit Cycle Oscillation ◽  
Cubic Phase ◽  
Phase Coupling ◽  
Quadratic Phase ◽  
Power Spectral ◽  
Cycle Oscillation ◽  
Higher Order Spectra

ABSTRACTHigher-Order Spectra (HOS) are used to characterise the nonlinear aeroelastic behaviour of a plunging and pitching 2-degree-of-freedom aerofoil system by diagnosing structural and/or aerodynamic nonlinearities via the nonlinear spectral content of the computed displacement signals. The nonlinear aeroelastic predictions are obtained from high-fidelity viscous fluid-structure interaction simulations. The power spectral, bi-spectral and tri-spectral densities are used to provide insight into the functional form of both freeplay and inviscid/viscous aerodynamic nonlinearities with the system displaying both low- and high-amplitude Limit Cycle Oscillation (LCO). It is shown that in the absence of aerodynamic nonlinearity (low-amplitude LCO) the system is characterised by cubic phase coupling only. Furthermore, when the amplitude of the oscillations becomes large, aerodynamic nonlinearities become prevalent and are characterised by quadratic phase coupling. Physical insights into the nonlinearities are provided in the form of phase-plane diagrams, pressure coefficient distributions and Mach number flowfield contours.

scholarly journals HIERARCHICAL HIGHER ORDER CRF FOR THE CLASSIFICATION OF AIRBORNE LIDAR POINT CLOUDS IN URBAN AREAS

2016 ◽  
Vol XLI-B3 ◽  
pp. 655-662 ◽  
Author(s):  
J. Niemeyer ◽  
F. Rottensteiner ◽  
U. Soergel ◽  
C. Heipke
Keyword(s):  
Urban Areas ◽  
Point Cloud ◽  
Conditional Random Field ◽  
Point Clouds ◽  
Higher Order ◽  
Airborne Lidar ◽  
Classification Result ◽  
3D Lidar ◽  
Point Level

We propose a novel hierarchical approach for the classification of airborne 3D lidar points. Spatial and semantic context is incorporated via a two-layer Conditional Random Field (CRF). The first layer operates on a point level and utilises higher order cliques. Segments are generated from the labelling obtained in this way. They are the entities of the second layer, which incorporates larger scale context. The classification result of the segments is introduced as an energy term for the next iteration of the point-based layer. This framework iterates and mutually propagates context to improve the classification results. Potentially wrong decisions can be revised at later stages. The output is a labelled point cloud as well as segments roughly corresponding to object instances. Moreover, we present two new contextual features for the segment classification: the <i>distance</i> and the <i>orientation of a segment with respect to the closest road</i>. It is shown that the classification benefits from these features. In our experiments the hierarchical framework improve the overall accuracies by 2.3% on a point-based level and by 3.0% on a segment-based level, respectively, compared to a purely point-based classification.

Spectral Analyses of Nonlinear Interactions

1995 ◽  
Author(s):  
Balakumar Balachandran ◽  
Khalil A. Khan
Keyword(s):  
Coupled Oscillators ◽  
Higher Order ◽  
Nonlinear Interactions ◽  
Phase Coupling ◽  
Spectral Analyses ◽  
Weakly Nonlinear ◽  
Numerical Studies ◽  
Analytical Approximations ◽  
Higher Order Spectra

Abstract Signals pertaining to motions of nonlinearly coupled oscillators are studied using higher-order spectral analyses. The analyses is used to understand the role of phase coupling in nonlinear interactions between two or more Fourier components. For certain motions of weakly nonlinear systems, analytical approximations are obtained for relevant higher-order spectra and coherence functions. Numerical studies are conducted to verify analytical predictions and to illustrate the usefulness of spectral analyses for different cases.

scholarly journals HIERARCHICAL HIGHER ORDER CRF FOR THE CLASSIFICATION OF AIRBORNE LIDAR POINT CLOUDS IN URBAN AREAS

2016 ◽  
Vol XLI-B3 ◽  
pp. 655-662 ◽  
Author(s):  
J. Niemeyer ◽  
F. Rottensteiner ◽  
U. Soergel ◽  
C. Heipke
Keyword(s):  
Urban Areas ◽  
Point Cloud ◽  
Conditional Random Field ◽  
Point Clouds ◽  
Higher Order ◽  
Airborne Lidar ◽  
Classification Result ◽  
3D Lidar ◽  
Point Level

We propose a novel hierarchical approach for the classification of airborne 3D lidar points. Spatial and semantic context is incorporated via a two-layer Conditional Random Field (CRF). The first layer operates on a point level and utilises higher order cliques. Segments are generated from the labelling obtained in this way. They are the entities of the second layer, which incorporates larger scale context. The classification result of the segments is introduced as an energy term for the next iteration of the point-based layer. This framework iterates and mutually propagates context to improve the classification results. Potentially wrong decisions can be revised at later stages. The output is a labelled point cloud as well as segments roughly corresponding to object instances. Moreover, we present two new contextual features for the segment classification: the <i>distance</i> and the <i>orientation of a segment with respect to the closest road</i>. It is shown that the classification benefits from these features. In our experiments the hierarchical framework improve the overall accuracies by 2.3% on a point-based level and by 3.0% on a segment-based level, respectively, compared to a purely point-based classification.

Sign in / Sign up

Export Citation Format

Share Document