Motor imagery data classification for BCI application using wavelet packet feature extraction

The noninvasive brain imaging modalities have provided us an extraordinary means for monitoring the working brain. Among these modalities, Electroencephalography (EEG) is the most widely used technique for measuring the brain signals under different tasks, due to its mobility, low cost, and high temporal resolution. In this paper we investigate the use of EEG signals in brain-computer interface (BCI) systems.

Determination of embedment depth of timber poles and piles using wavelet transform

This paper presents an investigation on the wave propagation in timber poles with Wavelet Transform (WT) analysis for identification of the condition and underground depth of embedded timber poles in service. Most of non-destructive testing (NDT) applications for timber poles using wave-based methods consider only single wave mode and no dispersion. However, for wave propagations in timber poles (damaged/undamaged), such simplification may not be correct, especially for broad band excitation using impulse impact. To investigate the problem, a 5m timber pole was investigated numerically and experimentally. A dispersion curve is generated from the numerical results to provide guidance on the velocity and wave mode selection. Continuous wavelet transform (CWT) is applied on the same signal to verify the presence of modes and to process data from experimental testing. The results are presented in both time domain and time-frequency domain for comparison. The results of the investigation showed that, wavelet transform analysis can be a reliable signal processing tool for NDT in terms of condition and embedment length determination.

Determinations of stress wave velocity in a timber pole using wavelet transform

This paper presents an application of Wavelet Transfonn (WT) for determination of stress wave velocity for Non-destructive Testing of timber utility poles in service. For surface Non-destructive Testing (NDT), the hammer impact, which produces generally broadband frequency excitation, is used to generate stress wave. Moreover, due to practicality the impact location for field testing of a utility pole is on the side of the pole and 1.5 m above ground level. And the geometry of utility pole could not guarantee non-dispersive longitudinal wave. All of these issues have resulted in lack of accuracy and reliability of results from surface NDT in field testing. In recognition of such problem, this research explores methods to reliably calculate desired wave velocity by isolating wave mode and studying dispersive nature of utility pole. Fast Fourier Transfonn (FFT) is firstly conducted to determine the suitable frequency from a stress wave data. Then WT is applied on the wave data mentioned to perfonn time-frequency analysis. Velocity can be detennined by time history data of desired frequency from WT results which will be compared with the available analytical solution for longitudinal wave velocity. The results of the investigation showed that wavelet transfonn analysis can be a reliable signal processing tool for non-destructive testing in tenns of velocity detennination, which in tum also helps to detennine the embedded length of the timber pole.

Ranking of fibre-reinforced composite plate surface finish quality by wavelet texture analysis

In the automotive and other industries, the visual appearance of external surfaces is a key factor in perceived product quality. Traditionally, the quality of an automotive surface finish has been judged by expert human auditors. A set of 17 fibre-reinforced composite plates was previously manufactured to have a range of surface finish qualities and these plates were ranked by three expert observers and also optically digitally imaged. Following validation of the previous rankings, the wavelet texture analysis (WTA) technique was applied to the digital photographs to derive an instrumental measure of surface finish quality based on the panel images. The rank correlation between the human expert surface finish quality ratings and those from the W TA image analysis process was found to be positive, large and statistically significant. This finding indicates that WTA could form the basis of an inexpensive and practical instrumental method for the ranking of fibre-reinforced composite surface finish quality.

Characterization and application of objective pilling classification to patterned fabrics

Previously, the authors proposed a new, simple method of frequency domain analysis based on the two-dimensional discrete wavelet transform to objectively measure the pilling intensity in sample fabric images. The method was further characterized, and the results obtained indicate that standard deviation and variance are the most appropriate measures of the dispersion of wavelet details coefficients for analysis, that the relationship between wavelet analysis scale and fabric inter-yarn pitch was empirically confirmed, and, that fabrics with random patterns do not appear to impact on the effectiveness of the analysis method.

A signal processing approach for elastic wave-based structural health monitoring using active piezoelectrics

A series of digital frequency filters (DFFs) were designed to screen diverse noises and the spectrographic analysis was conducted to isolate complex boundary reflection, which obscures the damage-induced signals. The scale-averaged wavelet power (SAP) technique was applied to enhance
the measurement accuracy of Time of Flight (TOF). As an example, the propagation characteristics of elastic wave in a structural beam of square cross-section were analyzed using such an approach and verified experimentally and numerically, with the consideration of the complicated wave scatter caused by the non-ignorable section dimensions.

Objective pilling evaluation of wool fabrics

An objective pilling evaluation method based on the multi-scale two-dimensional dual-tree complex wavelet transform and linear discriminant function of Bayes' Rule was developed. The surface fuzz and pills are identified from the high-frequency noise, fabric textures, fabric surface unevenness, and illuminative variation of a pilled fabric image by the two-dimensional dual-tree complex wavelet decomposition and reconstruction. The energies of the reconstructed subimages in six spatial orientations (±15º, ±45º, ±75º) are calculated as the elements of the pilling feature vector, whose dimension is reduced by principal component analysis. A linear discriminant function of Bayes' Rule was used as a classifier to establish classification rules among the five pilling grades. A new pilled sample with the same physical construction can then be automatically assigned to one of the five pilling grades by the classification rules. A general evaluation of the proposed method was conducted using the SM50 woven, non-woven, and SM54 knitted standard pilling test image sets. The results suggest that the new method can successfully establish classification rules among the five pilling grade groups for each of the three standard pilling test image sets and should be applicable to practical objective pilling evaluation.

Visual tracking of vehicles using multiresolution analysis and neural network

This paper describes the procedure for detection and tracking of a vehicle from an on-road image sequence taken by a monocular video capturing device in real time. The main objective of such a visual tracking system is to closely follow objects in each frame of a video stream, such that the object position as well as other geometric information are always known. In the tracking system described, the video capturing device is also moving. It is a challenge to detect and track a moving vehicle under a constantly changing environment coupled to real time video processing. The system suggested is robust to implement under different illuminating conditions by using the monocular video capturing device. The vehicle tracking algorithm is one of the most important modules in an autonomous vehicle system, not only it should be very accurate but also must have the safety of other vehicles, pedestrians, and the moving vehicle itself. In order to achieve this an algorithm of multi resolution technique based on Haar basis functions were used for the wavelet transform, where a combination of classification was carried out with the multilayer feed forward neural network. The classification is done in a reduced dimensional space, where principle component analysis (PCA) dimensional reduction technique has been applied to make the classification process much more efficient. The results show the effectiveness of the proposed methodology.

The robustness of objective fabric pilling evaluation method

Previously, we proposed a new method to identify fabric pilling and objectively measure fabric pilling intensity based on the two-dimensional dual-tree complex wavelet reconstruction and neural network classification. Here we further evaluate the robustness of the method. Our results indicate that the pilling identification method is robust to significant variation in the brightness and contrast of the image, rotation of the image, and 2 i (i is an integer) times dilation of the image. The pilling feature vector developed to characterize the pilling intensity is robust to brightness change but is sensitive to large rotations of the image. As long as all fabric images are adjusted to have the same contrast level and the sample is illuminated from the same direction, the pilling feature vectors are comparable and can be used to classify the pilling intensity.

New methods for objective evaluation of fabric pilling by frequency domain image processing

Fabric pilling is a serious problem for the apparel industry. Resistance to pilling is normally tested by simulated accelerated wear and manual assessment of degree of pilling based on a visual comparison of the sample to a set of test images. A number of automated systems based on image analysis have been developed. The authors propose new methods of image analysis based on the two-dimensional wavelet transform to objectively measure the pilling intensity in sample images. Initial work employed the detail coefficients of the two-dimensional discrete wavelet transform (2DDWT) as a measure of the pilling intensity of woven/knitted fabrics.

This method is shown to be robust to image translation and brightness variation. Using the approximation coefficients of the 2DDWT, the method is extended to non-woven pilling image sets. Wavelet texture analysis (WTA) combined with principal components analysis are shown to produce a richer texture description of pilling for analysis and classification. Finally, employing the two-dimensional dual-tree complex wavelet transform as the basis for the WTA feature vector is shown to produce good automated classification on a range of standard pilling image sets.

Performance of an objective fabric pilling evaluation method

In previous work, we established the principle of objective fabric pilling evaluation based on two-dimensional dual-tree complex wavelet transform (2DDTCWT) image reconstruction and non-linear classification using a neural network. This proof-of-principle work was performed using standard pilling test images. Here, we demonstrate the practical operation of the objective pilling evaluation method using a large set of real fabric pilling samples. We show that piling classification results from a trained multiple-layer perceptron neural network achieve a regression correlation of approximately 96% with the corresponding human expert pilling ratings.

Objective pilling evaluation of nonwoven fabrics

A pilled nonwoven fabric image consists of brightness variations caused by high frequency noise, randomly distributed fibers, fuzz and pills, fabric surface unevenness, and background illumination variance. They have different frequency and space distributions and thus can be separated by the two-dimensional dual-tree complex wavelet transform reconstructed detail and approximation images. The energies of the six direction detail sub-images, which capture brightness variation caused by fuzz and pills of different sizes, quantitatively characterize the pilling volume distribution at different directions and scales. They are used as pilling features and inputs of neural network supervised classifier. The initial results based on a nonwoven wool fabric standard pilling test image set, the Woolmark®‚ SM 50 Blanket set, suggest that this objective pilling evaluation method developed by the combination of pilling identification, characterization method and neural network supervised classifier is feasible.

Intelligent clothing for automated recognition of human physical activities in free-living environment

This paper presents an intelligent clothing framework for human daily activity recognition using a single waist-worn tri-axial accelerometer sensor coupled with a robust pattern recognition system. The activity recognition algorithm is realized to distinguish six different physical activities through three major steps: acceleration signal collection/pre-processing, wavelet-based principle component analysis, and a support vector machine classifier. The proposed activity recognition method has been experimentally validated through two batches of trials with an overall mean classification accuracy of 95.25 and 94.87%, respectively. These results suggest that the intelligent clothing is not only able to learn the activity patterns but also capable of generalizing new data from both known and unknown subjects. This enables the proposed intelligent clothing to be applied in a comfortable and in situ assessment of human physical activities, which would open up new market segments to the textile industry.

Spectral element model updating for damage identification using clonal selection algorithm

A spectral element model updating procedure is presented to identify damage in a structure using Guided wave propagation results. Two damage spectral elements (DSE1 and DSE2) are developed to model the local (cracks in reinforcement bar) and global (debonding between reinforcement bar and concrete) damage in one-dimensional homogeneous and composite waveguide, respectively. Transfer matrix method is adopted to assemble the stiffness matrix of multiple spectral elements. In order to solve the inverse problem, clonal selection algorithm is used for the optimization calculations. Two displacement-based functions and two frequency-based functions are used as objective functions in this study. Numerical simulations of wave propagation in a bare steel bar and in a reinforcement bar without and with various assumed damage scenarios are carried out. Numerically simulated data are then used to identify local and global damage of the steel rebar and the concrete-steel interface using the proposed method. Results show that local damage is easy to be identified by using any considered objective function with the proposed method while only using the wavelet energy-based objective function gives reliable identification of global damage. The method is then extended to identify multiple damages in a structure. To further verify the proposed method, experiments of wave propagation in a rectangular steel bar before and after damage are conducted. The proposed method is used to update the structural model for damage identification. The results demonstrate the capability of the proposed method in identifying cracks in steel bars based on measured wave propagation data.

An integrated method of feature extraction and objective evaluation of fabric pilling

A pilled fabric image consists of sub-images of different frequency components, and the fabric texture and the pilling information are in different frequency bands. Interference from fabric background texture affects the accuracy of computer-aided pilling ratings. A new approach for pilling evaluation based on the multi-scale two-dimensional dualtree complex wavelet transform (CWT) is presented in this paper to extract the pilling information from pilled fabric images. The CWT method can effectively decompose the pilled fabric image with six orientations at different scales and reconstruct fabric background texture and pilling sub-images. This study used an energy analysis method to search for an optimum image decomposition scale and dynamically discriminate pilling image from noise, fabric texture, fabric surface unevenness, and illuminative variation in the pilled fabric image. For pilling objective rating, six parameters were extracted from the pilling image to describe pill properties. A Levenberg-Marquardt backpropagation neural rule was used as a classifier to classify the pilling grade. The proposed method was evaluated using knitted, woven, and nonwoven pilled fabric images photographed with a digital camera.