Stationary Wavelet Transform Research Articles

GA-CNN: Analyzing student’s cognitive skills with EEG data using a hybrid deep learning approach

A cognitive state (CS) assessment can be effectively performed using Electroencephalogram (EEG). However, due to the curse of dimensionality issues of EEG, most of the clustering methods often lead to poor performance. Deep neural network-based representation learning transforms high-dimensional data into lower-dimensional feature space, increasing the performance of CS prediction in students. So, in this research, a novel graph-based conventional attention neural network (GA-CNN) is developed to reduce distribution differences while analyzing student performance. To perform this classification, the obtained EEG signal dataset is denoised with the help of Stationary Wavelet Transform (SWT) based Independent Component Analysis (ICA) that filters out the noise signals. Likewise, the behavioural dataset is pre-processed using zero normalization and Not a Number (NaN) value computation method. Then, the effective features are extracted from the pre-processed data using the Long-Short-Term-Memory (LSTM) technique. Finally, the GA-CNN model is initiated to classify the students’ cognitive state (CS). The proposed method is implemented using the MATLAB tool, and the performance of the expected GA-CNN model is compared to other approaches where the analysis is done using the benchmark Kaggle EEG data set. The classification accuracy is significantly improved compared to other methods. The model achieves 87% accuracy, 98% precision, 75% recall, and 85% F1 score, outperforming various methods and making a better compromise.

Partial discharge de-noising based on hybrid particle swarm optimization SWT adaptive threshold

A hybrid particle swarm optimization stationary wavelet adaptive threshold denoising (HPO-SWT-ATD) method was proposed to improve the adaptive ability of wavelet transform in partial discharge signal denoising. In the proposed method, the partial discharge signal is decomposed by stationary wavelet transform(SWT) and the multiorder differentiable function based on the Stein unbiased likelihood estimate (SURE) is used as the denoising threshold function. In threshold selection, the improved particle swarm optimization algorithm is used for global adaptive search to select the optimal denoising threshold. The de-noising experiments are carried out on the simulated partial discharge signals and the measured partial discharge signals.The experiment results show that, compared with the hard threshold method, particle swarm optimization threshold method, genetic algorithm optimization threshold method, Wiener filter method and modal decomposition method, the proposed method can better remove the white noise in the PD signal, and the denoising signal distortion degree is smaller.

Exploring Frequency Band-Based Biomarkers of EEG Signals for Mild Cognitive Impairment Detection.

Mild Cognitive Impairment (MCI) is often considered a precursor to Alzheimer's disease (AD), with a high likelihood of progression. Accurate and timely diagnosis of MCI is essential for halting the progression of AD and other forms of dementia. Electroencephalography (EEG) is the prevalent method for identifying MCI biomarkers. Frequency band-based EEG biomarkers are crucial for identifying MCI as they capture neuronal activities and connectivity patterns linked to cognitive functions. However, traditional approaches struggle to identify precise frequency band-based biomarkers for MCI diagnosis. To address this challenge, a novel framework has been developed for identifying important frequency sub-bands within EEG signals for MCI detection. In the proposed scheme, the signals are first denoised using a stationary wavelet transformation and segmented into small time frames. Then, four frequency sub-bands are extracted from each segment, and spectrogram images are generated for each sub-band as well as for the full filtered frequency band signal segments. This process produces five different sets of images for five separate frequency bands. Afterwards, a convolutional neural network is used individually on those image sets to perform the classification task. Finally, the obtained results for the tested four sub-bands are compared with the results obtained using the full bandwidth. Our proposed framework was tested on two MCI datasets, and the results indicate that the 16-32 Hz sub-band range has the greatest impact on MCI detection, followed by 4-8 Hz. Furthermore, our framework, utilizing the full frequency band, outperformed existing state-of-the-art methods, indicating its potential for developing diagnostic tools for MCI detection.

Online Removal of Cardiac Artifacts from Respiratory Surface Electromyograms

Surface electromyographic (sEMG) signals of the respiratory muscles can be used for assessing patient activity during mechanical ventilation. However, the measured signals are usually heavily contaminated by the electrical activity of the heart. In this paper, an online algorithm for real-time respiratory sEMG denoising by means of the stationary wavelet transform (SWT) is presented. It was analyzed on a dataset of healthy patients and was found to perform comparably to an offline SWT algorithm on several metrics. Online processing ofers the potential to improve the therapy of ventilated patients directly at the bedside.

Improving Cell Image Segmentation by Using Isotropic Undecimated Wavelet Transform

Improving Cell Image Segmentation by Using Isotropic Undecimated Wavelet Transform

An incremental high impedance fault detection method under non-stationary environments in distribution networks

In the non-stationary environments of distribution networks, where operating conditions continually evolve, maintaining reliable high impedance faults (HIF) detection is a significant challenge due to the frequent changes in data distribution caused by environmental variations. In this paper, we propose a novel HIF detection method based on incremental learning to handle non-stationary data stream with changing distributions. The proposed method utilizes stationary wavelet transform (SWT) to extract fault characteristics in different frequency domains from zero-sequence current data. Subsequently, a complex mapping from signal features to operational conditions is established using backpropagation neural network (BPNN) to achieve online detection of HIF. Additionally, signal features are analyzed using density-based spatial clustering of applications with noise (DBSCAN) to monitor the distribution of data. After encountering multiple distribution changes, an incremental learning process based on data replay is initiated to evolve the BPNN model for adapting to the changing data distribution. It is worth noting that the data replay mechanism ensures that the model retains previously acquired knowledge while learning from newly encountered data distributions. The proposed method was implemented in a prototype of a designed edge intelligent terminal and validated using a 10 kV testing system data. The experimental results indicate that the proposed method is capable of identifying and learning new distribution data information within non-stationary data stream. This enables the classifier model to maintain a high level of detection accuracy for the current cycle data, effectively enhancing the reliability of HIF detection.

Developing a hybrid CEEMDAN-PE-HE-SWT method to remove the noise of measured carbon dioxide blast wave

Monitoring the carbon dioxide blast wave is an efficient method for determining the power of carbon dioxide blasting. Due to the harsh measurement environment, noise is inevitably mixed into the recorded signals. This work proposed a hybrid denoising strategy based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), permutation entropy (PE), Hurst exponent (HE), and stationary wavelet transform (SWT). Firstly, the measured signal is decomposed by CEEMDAN, and then multiple intrinsic mode functions (IMFs) are divided into pure, mixed, and noisy by PE and HE. The noise in the mixed IMFs is removed by SWT. Finally, the blast wave is reconstructed through the pure and denoised mixed IMFs. The denoising performance of the proposed approach was compared with that of the other six approaches. The results indicate that the proposed approach has better performance and could be regarded as an effective denoising method for carbon dioxide blast waves.

EEG-based epileptic seizure detection using binary dragonfly algorithm and deep neural network

Electroencephalogram (EEG) is one of the most common methods used for seizure detection as it records the electrical activity of the brain. Symmetry and asymmetry of EEG signals can be used as indicators of epileptic seizures. Normally, EEG signals are symmetrical in nature, with similar patterns on both sides of the brain. However, during a seizure, there may be a sudden increase in the electrical activity in one hemisphere of the brain, causing asymmetry in the EEG signal. In patients with epilepsy, interictal EEG may show asymmetric spikes or sharp waves, indicating the presence of epileptic activity. Therefore, the detection of symmetry/asymmetry in EEG signals can be used as a useful tool in the diagnosis and management of epilepsy. However, it should be noted that EEG findings should always be interpreted in conjunction with the patient's clinical history and other diagnostic tests. In this paper, we propose an EEG-based improved automatic seizure detection system using a Deep neural network (DNN) and Binary dragonfly algorithm (BDFA). The DNN model learns the characteristics of the EEG signals through nine different statistical and Hjorth parameters extracted from various levels of decomposed signals obtained by using the Stationary Wavelet Transform. Next, the extracted features were reduced using the BDFA which helps to train DNN faster and improve its performance. The results show that the extracted features help to differentiate the normal, interictal, and ictal signals effectively with 100% accuracy, sensitivity, specificity, and F1 score with a 13% selected feature subset when compared to the existing approaches.

Wave-Atom and Cycle-Spinning-Based Noise Reduction in Mammography Images

Image denoising is crucial in medical image processing. Digital mammography depends significantly on de-noising for computer-aided-detection of malignant cells like Microcalcifications. In this work, we proposed an unique hybrid approach to reduce Gaussian noise in digital mammograms by combining the wave-atom translation and cycle spinning methods. Pictures denoised by thresholding of coefficients would produce pseudo-Gibbs events because wave atoms are not translationally invariant. Circular motion is applied to keep away the artefacts. Experimental results clearly establish that the method is effective at filtering out background noise while maintaining the integrity of edges and enhancing picture quality. Mini-Mias pictures with variable quantities of Gaussian Noise are used to evaluate and analyse the performance using peak signal-to-noise ratio and structural similarity index. The provided technique outperforms several current filters in terms of evaluated results of peak signal-to-noise ratio and structural similarity index.

Hybrid feature extraction and LLTSA-based dimension reduction for vein pattern recognition

ABSTRACT In information and security, the personal identification of individuals becomes much more important. For improving security, several biometric recognition techniques are implemented. However, in finger vein recognition, it faces the critical problem of fake finger vein images, security and less accuracy. To conquer this problem, Hybrid Feature Extraction with Linear Local Tangent Space Alignment-based dimension reduction and Support Vector Machine classifier (HFE–LLTSA–SVM) is proposed. In this hybrid, FE is considered as the combination of histogram of oriented gradients (HOG), grey-level co-occurrence matrix (GLCM), stationary wavelet transform (SWT), and local binary pattern (LBP) for extracting the hybrid feature. LLTSA perform dimension reduction in the outputs of HFE from HOG, GLCM, and LBP. Furthermore, SVM is used for classification which gives authentication based on error-correcting code. Finally, the performance parameters were calculated and the proposed method achieved better accuracy of 99.75%, when compared with existing methods.

Partial discharge based recognition of water droplets location in high voltage insulator using convolutional neural network – Bacterial foraging algorithm based optimized machine learning classifier

Measurement and analysis of Partial Discharge (PD) patterns have appeared as an emerging field in assessing insulation failure in High Voltage apparatus. This paper uses a PD signal combined with the deep convolution-optimized learning machine classifier (DC-OLMC) to predict the location of water droplets in 11 kV polymer insulators subjected to alternating currents. There are two major confront when applying the proposed algorithm: i) Contamination is a significant issue in PD signal measurement, which causes a reduction in recognition rate (RR), and ii) with minimal computing time, high-level feature extraction and recognition. Traditional condition monitoring methods of insulators concentrated on extracting fewer priority features from the input patterns. In the current work, to address this problem, an Alexnet with Bacterial Foraging Algorithm (BFO) based optimized kernel parameter classifier and Translation Invariant Wavelet Transform (TIWT) is employed to remove interference from PD signals. The analysis demonstrates that the suggested technique, with an identification rate of 99.17%, is considered a valuable tool for locating water droplets in high-voltage insulators.

An efficient image defogging algorithm based on dragonfly optimized gamma correction and stationary wavelet decomposition

Image dehazing is a revolutionary technique for restoring images with hazy or foggy landscapes, that has gotten a lot of focus in recent years since it gained importance in a surveillance system. However, the image processing by the traditional defogging algorithm has difficulties in integrating the depth of image detail and the color of the image. Therefore, in this paper, a novel framework based on wavelet decomposition and optimized gamma correction is proposed for efficaciously retrieving the fog-free image. The foggy image is first divided into low and high frequency sub-images using SWT (Stationary Wavelet Transform), which has the advantages of preserving temporal features so that information loss can be stopped. Then the low frequency and high frequency images are processed with defogging and denoising modules to remove fog and noise respectively. The DOGC (Dragonfly optimal Gamma Correction) algorithm in dehazing module dynamically enhanced the color detail information without human intervention so that observed scene contrast and visibility are well preserved. Lastly, fog-free image is reconstructed from sub-enhanced images. The experimental findings show that the proposed framework outperforms state-of-the-art methods in terms of both quantitative and qualitative assessment criteria using the established dataset. Furthermore, the proposed method efficiently removes fog while preserving the naturalness of fog images.

Multi-image Feature Map-Based Watermarking Techniques Using Transformer

Nowadays, protecting multimedia data is a significant challenge because of the advancement of technology and software. The embedding process heavily relies on watermarking to accomplish multimedia security in terms of content authentication, proof of ownership, and tamper detection. Our objective is to develop an invariant watermark that can survive different signal-processing attacks. We presented a unique hybrid technique (DWT-QR-SWT) and multi-image invariant features generated as a watermark using a Transformer encoder-decoder model. The encoded image features are subsampled using PCA in order to decrease the dimensionality of the watermark image. The first two images are used as watermark1 and the next two images as watermark2 to produce multi-watermark feature maps. To embed the watermark, a hybrid DWT-QR decomposition has been applied to the original image1. On the primary watermarked image, two Level Stationary Wavelet Transform (SWT) were applied to embed the secondary watermark2. At the extraction phase, the tampered image is recovered by passing the extracted watermark image as input to the transformer decoder. A multi-image watermark increases data embedding capabilities and also achieves two-level content authentication, tamper detection, localization, and recovery. With a PSNR of 59.05 dB, the testing result demonstrates great resilience and improved imperceptibility.

Application of translation wavelet transform with new threshold function in pulse wave signal denoising.

The wrist pulse wave under the optimal pulse pressure plays an important role in detecting human body's physiological and pathological information. Wavelet threshold filtering is a common method for pulse wave de-noising. However, traditional filtering methods cannot smoothen the whole pulse wave well and highlight the details. In view of this, an attempt is made in this paper to propose the pulse wave denoising algorithm for pulse wave under optimal pulse pressure according to the translation invariant wavelet transform (TIWT) and the new threshold function. Firstly, by using hyperbolic tangent curve and combining the advantages of soft threshold function and hard threshold function, the new threshold function is derived. Secondly, based on the TIWT, pseudo-Gibbs phenomenon gets suppressed. The experiments show that in comparison to the traditional wavelet filtering algorithm, the novel algorithm can better maintain the pulse wave geometric characteristics and has a higher signal to noise ratio (SNR). The TIWT with improved new threshold compensates the shortcomings of the traditional wavelet threshold denoising methods in a better way. It lays a foundation for extracting time-domain characteristics of pulse wave.

Historical Text Image Enhancement Using Image Scaling and Generative Adversarial Networks.

Historical documents such as newspapers, invoices, contract papers are often difficult to read due to degraded text quality. These documents may be damaged or degraded due to a variety of factors such as aging, distortion, stamps, watermarks, ink stains, and so on. Text image enhancement is essential for several document recognition and analysis tasks. In this era of technology, it is important to enhance these degraded text documents for proper use. To address these issues, a new bi-cubic interpolation of Lifting Wavelet Transform (LWT) and Stationary Wavelet Transform (SWT) is proposed to enhance image resolution. Then a generative adversarial network (GAN) is used to extract the spectral and spatial features in historical text images. The proposed method consists of two parts. In the first part, the transformation method is used to de-noise and de-blur the images, and to increase the resolution effects, whereas in the second part, the GAN architecture is used to fuse the original and the resulting image obtained from part one in order to improve the spectral and spatial features of a historical text image. Experiment results show that the proposed model outperforms the current deep learning methods.

Effect of auditory noise circumstance on visual images encoding based electroencephalography analysis

ABSTRACT Auditory stimulation may be beneficial or detrimental to human cognitive and memory processing. Numerous studies have been conducted to investigate the influence of various sounds on human performance. The current research discovers the impact of auditory white noise on the memory performance of 60 college students using different difficulty levels in visual object-number pair assessment. Memory perfomance is accessed based on the assessment recall scores and brain activities. An electroencephalography (EEG) device measures and records the brain's electrical activity during the experimental session. Nine EEG channel locations are selected for brain activities analysis. The raw EEG dataset is processed using wavelet methods of stationary wavelet transform (SWT) and discrete wavelet transfrom (DWT) using the Daubechies (db) function to eliminate the artifact components and extract the required EEG features. The result indicated that the college student remembered the object-number pair assessment better under auditory white noise rather than no audio condition. This contributed from the activation of alpha, theta, gamma, and beta activities that increased the subject's attention, alertness, and sensory processing during memorizing. Therefore, it is suggested that the auditory white noise should be listened to during remembering and learning visual items, which can boost memory performance.

Probabilistic Forecasting of Residential Energy Consumption Based on SWT-QRTCN-ADSC-NLSTM Model

Residential electricity consumption forecasting plays a crucial role in the rational allocation of resources reducing energy waste and enhancing the grid-connected operation of power systems. Probabilistic forecasting can provide more comprehensive information for the decision-making and dispatching process by quantifying the uncertainty of electricity load. In this study, we propose a method based on stationary wavelet transform (SWT), quantile regression (QR), Bidirectional nested long short-term memory (BiNLSTM), and Depthwise separable convolution (DSC) combined with attention mechanism for electricity consumption probability prediction methods. First, the data sequence is decomposed using SWT to reduce the complexity of the sequence; then, the combined neural network model with attention is used to obtain the prediction values under different quantile conditions. Finally, the probability density curve of electricity consumption is obtained by combining kernel density estimation (KDE). The model was tested using historical demand-side data from five UK households to achieve energy consumption predictions 5 min in advance. It is demonstrated that the model can achieve both reliable probabilistic prediction and accurate deterministic prediction.

Multisegmented Intelligent Solution for MT-HVDC Grid Protection

Fault detection continues to be a relevant and ongoing topic in multiterminal High Voltage Direct Current (MT-HVDC) grid protection. In MT-HVDC grids, however, high DC-fault currents result from a failure of a complex protective threshold in traditional protection schemes, making Voltage Source Converter (VSC) vulnerable to such potent transient currents. In this innovative single-ended DC protection scheme, multiple time window segments are used to consider the effects of the transient period across limiting inductors at each end of the link. Multiple segments of 0–0.8, 0.8–1.5, and 1.5–3.0 ms reduce relay failure and improve the sensitivity to high fault impedance while requiring minimal computational effort. It employs feature extraction tools such as Stationary Wavelet Transform and Random Search (RS)-based Artificial Neural Networks (ANNs) for detecting transmission line faults within DC networks. Its goal is to improve the accuracy and reliability of protective relays as a result of various fault events. Simulations showed that the proposed algorithms could effectively identify any input data segment and detect DC transmission faults up to 500 ohms. Accuracy for the first segment is 100% for fault impedance up to 200 ohms, whereas the second and third segments show 100% accuracy for high impedance faults up to 400 ohms. In addition, they maintain 100% stability even under external disturbances.

12-lead ECG signal processing and atrial fibrillation prediction in clinical practice.

Because clinically used 12-lead electrocardiography (ECG) devices have high falsepositive errors in automatic interpretations of atrial fibrillation (AF), they require substantial improvements before use. A clinical 12-lead ECG pre-processing method with a parallel convolutional neural network (CNN) model for 12-lead ECG automatic AF recognition is introduced. Raw AF diagnosis data from a 12-lead ECG device were collected and analyzed by two cardiologists to differentiate between true- and false-positives. Using a stationary wavelet transform (SWT) and independent component analysis (ICA) noise reduction was conducted and baseline wandering was corrected for the raw signals. AF patterns were learned and predicted using a parallel CNN deep learning (DL) model. (1) The proposed method alleviates the decreased ECG QRS amplitude enhances the signal-to-noise ratio and clearly shows atrial and ventricular activities. (2) After training, the CNNbased AF detector significantly reduced false-positive errors. The precision of AF diagnosis increased from 77.3% to 94.0 ± 1.5% as compared to ECG device interpretation. For AF screening, the model showed an average sensitivity of 96.8 ± 2.2%, specificity of 79.0 ± 5.8%, precision of 94.0 ± 1.5%, F1-measure of 95.2 ± 1.0%, and overall accuracy of 92.7 ± 1.5%. The method can bridge the gap between the research and clinical practice The ECG signal pre-processing and DL-based AF interpretation can be rapidly implemented clinically.

A Novel CS 2G-starlet denoising method for high noise astronomical image

In deep space exploration, astronomical images are easily contaminated by noise, which affects image quality. However, for the denoising of high-noise astronomical images, obtaining good reconstruction results from the current denoising methods is difficult. This paper proposes a novel compressed sensing (CS) 2G-starlet denoising (NCSSD) method can effectively improve the reconstruction quality of astronomical images. Firstly, the proposed 2G-starlet Wiener filtering operator is used to select these starlet coefficients in the process of sparse image transformation. Then, a novel iterative stepsize operator is proposed to enhance the convergence ability of the algorithm. At the same time, an optimized cycle spinning method is proposed to adjust the reconstructed image. Through extensive simulation experiments and deep theoretical analysis and verification, the effectiveness of this method in high-noise astronomical image denoising is fully proven, and the quality of reconstructed image is improved. The proposed method has been successfully interconnected with the telescope and industrial camera, realizing the rapid acquisition of high-quality astronomical images. The research results of this article have important value for promoting the effective acquisition and analysis of astronomical images in exploring deep space.