The effects on classifier performance of 2D discrete wavelet transform analysis and whale optimization algorithm for recognition of power quality disturbances

Power Quality (PQ) is becoming more and more important day by day in the electric network. Signal processing, pattern recognition and machine learning are increasingly being studied for the automatic recognition of any disturbances that may occur during the generation, transmission, and distribution of electricity. There are three main steps to identify the PQ disturbances. These include the use of signal processing methods to calculate the features representing the disturbances, the selection of those that are more useful than these feature sets to prevent the creation of a complex classification model, the creating a classification model that recognizes multiple classes using the selected feature subsets. In this study, one-dimensional (1D) PQ disturbances signals are transformed into two-dimensional (2D) signals, 2D discrete wavelet transforms (2D-DWT) are used to extract the features. The features are extracted by using the wavelet families such as Daubechies, Biorthogonal, Symlets, Coiflets and Fejer-Korovkin in 2D-DWT to analyze PQ disturbances. Whale Optimization Algorithm (WOA) and k-nearest neighbor (KNN) classifier determine the feature subsets. Then, WOA and k nearest neighbor (KNN) classifier are used to determine the feature group. By using KNN and Support Vector Machines (SVM) classification methods, Classifier models that distinguish PQ disturbances are formed. The main aim of the study is to determine the features derived from 2D wavelet coefficients for different wavelet families and to determine which of them has a better classification performance to distinguish PQ disturbances signals. At the same time, different classification methods are simulated and a model which can classify PQ disturbances signals with high performance is created. Also, the generated models are analysed for their performance in terms of different noise levels (40 dB, 30 dB, 20 dB). The result of this simulation study shows that the model developed to classify PQ disturbances is superior to conventional models and other 2D signal processing methods in the literature. In addition, it was concluded that the proposed method can cope better with noisy signals by low computational complexity and higher classification rate.     

Generating complementary gray-level images for object recognition experiments using Gabor wavelet decomposition

We present a software image processing methodology to generate complementary gray-scale images for visual perception experiments examining the interaction between the spatial localization and orientation sensitivity of visual perception. Specifically, our system is able to selectively mask or unmask specific resolutions, positions, and/or orientations of an input gray-level image using Gabor wavelet decomposition. The resulting representations are then combined to obtain partially reconstructed images for novel psychophysical experimentations.     

Phase congruency: A low-level image invariant

 Phase congruency is a low-level invariant property of image features. Interest in low-level image invariants has been limited. This is surprising, considering the fundamental importance of being able to obtain reliable results from low-level image operations in order to successfully perform any higher level operations. However, an impediment to the use of phase congruency to detect features has been its sensitivity to noise. This paper extends the theory behind the calculation of phase congruency in a number of ways. An effective method of noise compensation is presented that only assumes that the noise power spectrum is approximately constant. Problems with the localization of features are addressed by introducing a new, more sensitive measure of phase congruency. The existing theory that has been developed for 1D signals is extended to allow the calculation of phase congruency in 2D images. Finally, it is argued that high-pass filtering should be used to obtain image information at different scales. With this approach, the choice of scale only affects the relative significance of features without degrading their localization. Received: 20 November 1998 / Accepted: 29 September 1999     

A practical guide to time-frequency analysis in the study of human motor behavior: the contribution of wavelet transform

The authors present a practical guide for studying nonstationary data on human motor behavior in a time-frequency representation. They explain the limits of classical methods founded exclusively on the time or frequency basis and then answer those limits with the windowed Fourier transform and the wavelet transform (WT) methods, both of which are founded on time-frequency bases. The authors stress an interest in the WT method because it permits access to the whole complexity of a signal (in terms of time, frequency, amplitude, and phase). They then show that the WT method is well suited for the analysis of the interaction between two signals, particularly in human movement studies. Finally, to demonstrate its practical applications, the authors apply the method to real data.     

A wavelet packet model of evoked potentials

The standard methods for decomposition and analysis of evoked potentials are bandpass filtering, identification of peak amplitudes and latencies, and principal component analysis (PCA). We discuss the limitations of these and other approaches and introduce wavelet packet analysis. Then we propose the "single-channel wavelet packet model," a new approach in which a unique decomposition is achieved using prior time-frequency information and differences in the responses of the components to changes in experimental conditions. Orthogonal sets of wavelet packets allow a parsimonious time-frequency representation of the components. The method allows energy in some wavelet packets to be shared among two or more components, so the components are not necessarily orthogonal. The single-channel wavelet packet model and PCA both require constraints to achieve a unique decomposition. In PCA, however, the constraints are defined by mathematical convenience and may be unrealistic. In the single-channel wavelet packet model, the constraints are based on prior scientific knowledge. We give an application of the method to auditory evoked potentials recorded from cats. The good frequency resolution of wavelet packets allows us to separate superimposed components in these data. Our present approach yields estimates of component waveforms and the effects of experiment conditions on the amplitude of the components. We discuss future extensions that will provide confidence intervals and p values, allow for latency changes, and represent multichannel data.     

Time-frequency analysis of single-sweep event-related potentials by means of fast wavelet transform

A time-frequency decomposition was applied to the event-related potentials (ERPs) elicited in an auditory oddball condition to assess differences in cognitive information processing. Analysis in the time domain has revealed that cognitive processes are reflected by various ERP components such as N1, P2, N2, P300, and late positive complex. However, the heterogeneous nature of these components has been strongly emphasized due to simultaneously occurring processes. The wavelet transform (WT), which decomposes the signal onto the time-frequency plane, allows the time-dependent and frequency-related information in ERPs to be captured and precisely measured. A four-octave quadratic B-spline wavelet transform was applied to single-sweep ERPs recorded in an auditory oddball paradigm. Frequency components in delta, theta, and alpha ranges reflected specific aspects of cognitive information processing. Furthermore, the temporal position of these components was related to specific cognitive processes.     

High capacity adaptive image steganography with cover region selection using dual-tree complex wavelet transform

The importance of image steganography is unquestionable in the field of secure multimedia communication. Imperceptibility and high payload capacity are some of the crucial parts of any mode of steganography. The proposed work is an attempt to modify the edge-based image steganography which provides higher payload capacity and imperceptibility by making use of machine learning techniques. The approach uses an adaptive embedding process over Dual-Tree Complex Wavelet Transform (DT-CWT) subband coefficients. Machine learning based optimization techniques are employed here to embed the secret data over optimal cover-image-blocks with minimal retrieval error. The embedding process will create a unique secret key which is imperative for the retrieval of data and need to be transmitted to the receiver side via a secure channel. This enhances the security concerns and avoids data hacking by intruders. The algorithm performance is evaluated with standard benchmark parameters like PSNR, SSIM, CF, Retrieval error, BPP and Histogram. The results of the proposed method show the stego-image with PSNR above 50 dB even with a dense embedding of up to 7.87 BPP. This clearly indicates that the proposed work surpasses the state-of-the-art image steganographic systems significantly.     

The role of higher order image statistics in masking scene gist recognition

In the present article, we investigated whether higher order image statistics, which are known to be carried by the Fourier phase spectrum, are sufficient to affect scene gist recognition. In Experiment 1, we compared the scene gist masking strength of four masking image types that varied in their degrees of second- and higher order relationships: normal scene images, scene textures, phase-randomized scene images, and white noise. Masking effects were the largest for masking images that possessed significant higher order image statistics (scene images and scene textures) as compared with masking images that did not (phase-randomized scenes and white noise), with scene image masks yielding the largest masking effects. In a control study, we eliminated all differences in the second-order statistics of the masks, while maintaining differences in their higher order statistics by comparing masking by scene textures rather than by their phase-randomized versions, and showed that the former produced significantly stronger gist masking. Experiments 2 and 3 were designed to test whether conceptual masking could account for the differences in the strength of the scene texture and phase-randomized masks used in Experiment 1, and revealed that the recognizability of scene texture masks explained just 1% of their masking variance. Together, the results suggest that (1) masks containing the higher order statistical structure of scenes are more effective at masking scene gist processing than are masks lacking such structure, and (2) much of the disruption of scene gist recognition that one might be tempted to attribute to conceptual masking is due to spatial masking.     

Stereo and motion cues in preattentive vision processing--some experiments with random-dot stereographic image sequences

Low-level preattentive vision processing is of special interest since it seems the logical starting point of all vision processing. Exploration of the human visual processing system at this level is, however, extremely difficult, but can be facilitated by the use of stroboscopic presentation of sequences of random-dot stereograms, which contain only local spatial and temporal information and therefore limit the processing of these images to the low level. Four experiments are described in which such sequences were used to explore the relationships between various cues (optical flow, stereo disparity, and accretion and deletion of image points) at the low level. To study these relationships in more depth, especially the resolution of conflicting information among the cues, some of the image sequences presented information not usually encountered in 'natural' scenes. The results indicate that the processing of these cues is undertaken as a set of cooperative processes.     

A two-fold transformation model for human action recognition using decisive pose

Human action recognition in videos is a tough task due to the complex background, geometrical transformation and an enormous volume of data. Hence, to address these issues, an effective algorithm is developed, which can identify human action in videos using a single decisive pose. To achieve the task, a decisive pose is extracted using optical flow, and further, feature extraction is done via a two-fold transformation of wavelet. The two-fold transformation is done via Gabor Wavelet Transform (GWT) and Ridgelet Transform (RT). The GWT produces a feature vector by calculating first-order statistics values of different scale and orientations of an input pose, which have robustness against translation, scaling and rotation. The orientation-dependent shape characteristics of human action are computed using RT. The fusion of these features gives a robust unified algorithm. The effectiveness of the algorithm is measured on four publicly datasets i.e. KTH, Weizmann, Ballet Movement, and UT Interaction and accuracy reported on these datasets are 96.66%, 96%, 92.75% and 100%, respectively. The comparison of accuracies with similar state-of-the-arts shows superior performance.     

心理表征的可视化途径：基于噪音的反向相关图像分类技术

社会心理学对图像的心理表征研究一直难以将心理活动的内容准确刻画出来。近10年来出现了一种新心理物理学方法——“反向相关图像分类技术”, 该技术假定观察者的反应与视觉噪音存在相关关系, 且反应是依照观察者的社会判断标准进行而非随机做出; 通过对其做出反应的相应噪音模式的足够次数的权重计算与视觉代码显现, 从而将观察者内在的评估特点可视化。该技术已在特质研究、种族和群际偏见等领域取得了一些成果, 但是未来仍需解决实验次数过多, 分离混杂的噪音以及被试的表现等问题, 才能获得更为真实的心理表征。     

Shedding light on words and sentences: near-infrared spectroscopy in language research

Investigating the neuronal network underlying language processing may contribute to a better understanding of how the brain masters this complex cognitive function with surprising ease and how language is acquired at a fast pace in infancy. Modern neuroimaging methods permit to visualize the evolvement and the function of the language network. The present paper focuses on a specific methodology, functional near-infrared spectroscopy (fNIRS), providing an overview over studies on auditory language processing and acquisition. The methodology detects oxygenation changes elicited by functional activation of the cerebral cortex. The main advantages for research on auditory language processing and its development during infancy are an undemanding application, the lack of instrumental noise, and its potential to simultaneously register electrophysiological responses. Also it constitutes an innovative approach for studying developmental issues in infants and children. The review will focus on studies on word and sentence processing including research in infants and adults.     

Oscillatory brain dynamics, wavelet analysis, and cognition

On the basis of a systems theoretical approach it was hypothesized that event-related potentials (ERPs) are superpositions of stimulus-evoked and time-locked EEG rhythms reflecting resonance properties of the brain (Ba?ar, 1980). This approach led to frequency analysis of ERPs as a way of analyzing evoked rhythms. The present article outlines the basic features of ERP frequency analysis in comparison to ERP wavelet analysis, a recently introduced method of time-frequency analysis. Both methods were used in an investigation of the functional correlates of evoked rhythms where auditory and visual ERPs were recorded from the cat brain. Intracranial electrodes were located in the primary auditory cortex and in the primary visual cortex thus permitting "cross-modality" experiments. Responses to adequate stimulation (e.g., visual ERP recorded from the visual cortex) were characterized by high amplitude alpha (8-16 Hz) responses which were not observed for inadequate stimulation. This result is interpreted as a hint at a special role of alpha responses in primary sensory processing. The results of frequency analysis and of wavelet analysis were quite similar, with possible advantages of wavelet methods for single-trial analysis. The results of frequency analysis as performed earlier were thus confirmed by wavelet analysis. This supports the view that ERP frequency components correspond to evoked rhythms with a distinct biological significance.     

Image processing for improved eye-tracking accuracy

Video cameras provide a simple, noninvasive method for monitoring a subject’s eye movements. An important concept is that of the resolution of the system, which is the smallest eye movement that can be reliably detected. While hardware systems are available that estimate direction of gaze in real time from a video image of the pupil, such systems must limit image processing to attain real-time performance and are limited to a resolution of about 10 arc minutes. Two ways to improve resolution are discussed. The first is to improve the image processing algorithms that are used to derive an estimate. Offline analysis of the data can improve resolution by at least one order of magnitude for images of the pupil. A second avenue by which to improve resolution is to increase the optical gain of the imaging setup (i.e., the amount of image motion produced by a given eye rotation). Ophthalmoscopic imaging of retinal blood vessels provides increased optical gain and improved immunity to small head movements but requires a highly sensitive camera. The large number of images involved in a typical experiment imposes great demands on the storage, handling, and processing of data. A major bottleneck had been the real-time digitization and storage of large amounts of video imagery, but recent developments in video compression hardware have made this problem tractable at a reasonable cost. Images of both the retina and the pupil can be analyzed successfully using a basic toolbox of image-processing routines (filtering, correlation, thresholding, etc.), which are, for the most part, well suited to implementation on vectorizing supercomputers.     

Visual image analysis by square wavelets: empirical evidence supporting a theoretical agreement between wavelet analysis and receptive field organization of visual cortical neurons

It was proposed that the human visual system analyzes images into square wavelets. To test this view, comparisons were made between the perceived similarity-dissimilarity of alphabet letters and the wavelet analyses of those same letters. For the proposal to be considered tenable, the coefficients of the wavelet analysis of similar letters must be similar, and the coefficients of the wavelet analysis of dissimilar letters must be dissimilar. From a selection of 12 letters, four pairs of letters had been reported by Van der Heijden, Mathas, and Van den Roovaart as very similar, and four other pairs of letters dissimilar. Each of the 12 letters was separately depicted in 8 x 8 matrices, and the signal represented by each of the matrices was analyzed into square wavelets using a new and original procedure which yielded a single set of coefficients for each matrix. Correlations between sets of coefficients were high (r ranged from .88 to .58) for those letter pairs judged high in similarity; correlations were low (r ranged from -.02 to .29) for those letter pairs judged low in similarity. When the correlations between the coefficients of wavelets of all eight-letter pairs were compared with the judged similarity-dissimilarity of all eight-letter pairs, the linear agreement was statistically significant. Agreement was found between the neurophysiological mapping of receptive fields of visual cortical neurons and the vectors or the pattern of pluses and minuses which characterized the wavelet analysis. Furthermore, regeneration of the visual image, or the pattern of neural activity representing the image, could be described by a tree-like flow of information among visual cortical neurons which received response data from visual receptive fields, the response data being wavelet coefficients. Results indicate the analysis accurately produces reliable transformations of visual patterns and may be a process used by the visual system.     

Functional magnetic resonance imaging: Overview and methods for psychological research

Functional magnetic resonance imaging (fMRI) allows noninvasive imaging of hemodynamic changes related to neural activity. This technique can be used in single-subject designs and can provide millimeter spatial resolution and temporal resolution in the range of 5–10 sec. This paper provides a brief introduction to MRI techniques and their application to functional neuroimaging, focusing on methodological issues that are of particular concern to psychologists, including methods for presenting computerized stimuli to subjects without disrupting the scanner, experimental design issues, and statistical analysis and image processing procedures. To illustrate methodological issues, recent results from a series of studies looking at the topographic organization of visual cortex are presented. General issues concerning limitations in this technique, future directions in its development, its relationship to other neuroimaging techniques, and the role of functional neuroimaging in psychological research are addressed in the Discussion.     

Structure and strategy in image generation

Two experiments were conducted to test a prediction of the Kosslyn & Shwartz computer simulation model of mental image processing. According to this model, more complex images require more time to form because parts are placed sequentially, and larger images require more time to form than smaller ones because more parts are placed. If these accounts are correct, then the advantage of forming a small image (i.e., one that seems to subtend a smaller visual angle) should be greater for more complex objects because the difference in number of parts imaged at the two sizes will be greater than with simpler objects. This prediction was confirmed only when subjects were not motivated to form highly elaborated images at small sizes. When subject tried to include all details, it actually took longest to form images of complex objects at small sizes. Both of these results support the central assumption of the Kosslyn-Shwartz model, namely the existence of a fixed resolution analog spatial medium.     

Feedback training for facial image comparison

People are typically poor at matching the identity of unfamiliar faces from photographs. This observation has broad implications for face matching in operational settings (e.g., border control). Here, we report significant improvements in face matching ability following feedback training. In Experiment 1, we show cumulative improvement in performance on a standard test of face matching ability when participants were provided with trial-by-trial feedback. More important, Experiment 2 shows that training benefits can generalize to novel, widely varying, unfamiliar face images for which no feedback is provided. The transfer effect specifically benefited participants who had performed poorly on an initial screening test. These findings are discussed in the context of existing literature on unfamiliar face matching and perceptual training. Given the reliability of the performance enhancement and its generalization to diverse image sets, we suggest that feedback training may be useful for face matching in occupational settings.     

A perceptually based comparison of image similarity metrics

The assessment of how well one image matches another forms a critical component both of models of human visual processing and of many image analysis systems. Two of the most commonly used norms for quantifying image similarity are L1 and L2, which are specific instances of the Minkowski metric. However, there is often not a principled reason for selecting one norm over the other. One way to address this problem is by examining whether one metric, better than the other, captures the perceptual notion of image similarity. This can be used to derive inferences regarding similarity criteria the human visual system uses, as well as to evaluate and design metrics for use in image-analysis applications. With this goal, we examined perceptual preferences for images retrieved on the basis of the L1 versus the L2 norm. These images were either small fragments without recognizable content, or larger patterns with recognizable content created by vector quantization. In both conditions the participants showed a small but consistent preference for images matched with the L1 metric. These results suggest that, in the domain of natural images of the kind we have used, the L1 metric may better capture human notions of image similarity.