Lifting Wavelet Research Articles

An interpretable multiscale lifting wavelet contrast network for planetary gearbox fault diagnosis with small samples

Previous deep learning-based fault diagnosis methods for planetary gearbox require numerous training samples and lack the necessary interpretability. Aiming at the problems of insufficient interpretability of deep models and the absence of feature mining capability with small samples, this study presents an interpretable multiscale lifting wavelet contrast network for planetary gearbox fault diagnosis. First, an interpretable multiscale lifting wavelet network is designed to achieve comprehensive and credible features mining from fault signals. Secondly, an interactive channel attention mechanism is constructed to choose feature maps with different frequency components. It can further confirm the interpretability of the lifting wavelet layer while improving the accuracy of the model. Finally, a time-frequency contrast loss is designed to simultaneously optimizing the distribution of time-frequency domain features. The effectiveness and interpretability of the model are analyzed through various visualization approaches. Experimental results on two planetary gearbox datasets indicate that our method is an interpretable and effective fault recognition method with small samples, and it holds a promising future for engineering applications.

Improving the performance of non-DC-biased optical OFDM with lazy lifting wavelet transform

Improving the performance of non-DC-biased optical OFDM with lazy lifting wavelet transform

An intelligent wireless channel corrupted image-denoising framework using symmetric convolution-based heuristic assisted residual attention network

ABSTRACT Image denoising is one of the significant approaches for extracting valuable information in the required images without any errors. During the process of image transmission in the wireless medium, a wide variety of noise is presented to affect the image quality. For efficient analysis, an effective denoising approach is needed to enhance the quality of the images. The main scope of this research paper is to correct errors and remove the effects of channel degradation. A corrupted image denoising approach is developed in wireless channels to eliminate the bugs. The required images are gathered from wireless channels at the receiver end. Initially, the collected images are decomposed into several regions using Adaptive Lifting Wavelet Transform (ALWT) and then the “Symmetric Convolution-based Residual Attention Network (SC-RAN)” is employed, where the residual images are obtained by separating the clean image from the noisy images. The parameters present are optimized using Hybrid Energy Golden Tortoise Beetle Optimizer (HEGTBO) to maximize efficiency. The image denoising is performed over the obtained residual images and noisy images to get the final denoised images. The numerical findings of the developed model attain 31.69% regarding PSNR metrics. Thus, the analysis of the developed model shows significant improvement.

VLSI design for adjustable compression rate in lossless/lossy compression of EEG signal

In the realm of remote health monitoring, the compression of electroencephalography (EEG) signals at the edge holds significant importance. This paper presents a VLSI structure capable of adjustable compression rates to achieve both lossless and lossy compression of EEG data, catering to environments requiring flexible adjustment of compression types and rates. The architecture integrates two-dimensional discrete wavelet transform (2D-DWT) and the Set Partitioning in Hierarchical Trees (SPIHT). Notably, the Haar wavelet lifting structure is employed in 2D-DWT, and the SPIHT scanning sequence is optimized for enhanced resource efficiency. The proposed algorithm is validated using the CHB-MIT Scalp EEG Database, demonstrating compression ratios of ≥1.95 for normal EEG and ≥1.69 for epileptic EEG. Through synthesis and layout design in the 130 nm CMOS technology, the resulting circuit achieves a maximum clock frequency of 57 MHz and occupies an area of 81 kμm2, with an average power consumption of less than 0.71nj per data for 16-bit data. These findings affirm the efficacy of the proposed VLSI structure for achieving efficient lossless/lossy compression of edge EEG data.

SEA-GWNN: Simple and Effective Adaptive Graph Wavelet Neural Network

The utilization of wavelet-based techniques in graph neural networks (GNNs) has gained considerable attention, particularly in the context of node classification. Although existing wavelet-based approaches have shown promise, they are constrained by their reliance on pre-defined wavelet filters, rendering them incapable of effectively adapting to signals that reside on graphs based on tasks at hand. Recent research endeavors address this issue through the introduction of a wavelet lifting transform. However, this technique necessitates the use of bipartite graphs, causing a transformation of the original graph structure into a bipartite configuration. This alteration of graph topology results in the generation of undesirable wavelet filters, thereby undermining the effectiveness of the method. In response to these challenges, we propose a novel simple and effective adaptive graph wavelet neural network (SEA-GWNN) class that employs the lifting scheme on arbitrary graph structures while upholding the original graph topology by leveraging multi-hop computation trees. A noteworthy aspect of the approach is the focus on local substructures represented as acyclic trees, wherein the lifting strategy is applied in a localized manner. This locally defined lifting scheme effectively combines high-pass and low-pass frequency information to enhance node representations. Furthermore, to reduce computing costs, we propose to decouple the higher- order lifting operators and induce them from the lower-order structures. Finally, we benchmark our model on several real- world datasets spanning four distinct categories, including citation networks, webpages, the film industry, and large-scale graphs and the experimental results showcase the efficacy of the proposed SEA-GWNN.

REAL-TIME IMPLEMENTATION OF LWT BASED NOVEL IR AND VI FUSION ALGORITHM USING RASPBERRY PI PLATFORM

One of the most important and active areas of image processing research is visible and thermallight image fusion. Moreover, real-time visible and thermal-light image fusion has been utilized in multiple kinds of applications such as surveillance devices, military applications, medical diagnosis, remote sensing, etc. Hence, this paper suggests a real-time application of visible and infrared (V-I) image fusion using lift wavelet transform (LWT) and implemented on the Raspberry Pi. The proposed morphological operations-based unsharp masking enhancement technique overcomes the low contrast issue of the fused image. Next, the LWT provides the good feature (smooth and detail) layers of visible image (VI) and infrared image (IRI) when compared to other transformations. Due to this, we have overcome the problem of spatial distortions in the fused image. Moreover, the proposed novel fusion techniques such as, mean-weighted fusion rule based on filters and max-weighted fusion rule based on filters generate the fused image with improved texture information and overcome the problem of edge information loss. The real-time application of the V-I image fusion is implemented through the portable hardware device Raspberry Pi. Finally, the experimental results show that the suggested framework has produced a fused image with improved visual quality, rich edge information, high contrast, low spatial distortions, and more texture information, when compared to the results of existing methodologies.

GA-GWNN: Generalized Adaptive Graph Wavelet Neural Network

Wavelet-based graph neural networks have received increasing attention in the node classification task. Existing graph wavelet-based approaches, however, are not applicable to arbitrary graphs as they use predefined wavelet filters with built-in homophilic assumptions and disregard heterophily. Recent studies attempted to address this issue through a wavelet lifting transform, which requires a bipartite graph, therefore altering the graph topology and leading to undesirable wavelet filters. This paper proposes a generalized adaptive graph wavelet network that preserves the graph topology through computational trees while implementing the lifting scheme on arbitrary graphs. Moreover, this locally defined lifting scheme integrates both high-pass and low-pass frequency components to further enhance feature representation. Finally, we benchmark our model using nine homophilic and heterophilic datasets, and the results demonstrate the effectiveness of our method.

Lifting Wavelets with OGS for Doppler Profile Estimation

This article discusses the second-generation wavelet transform concept and technique and its application to the noise removal problem of MST radar data. Located near Gadanki in Andhra Pradesh, India, the MST radar is collecting data on climate change. To obtain weather data, the signal collected by the radar needs to be analyzed, which usually requires power spectrum estimation. Most parametric and non-parametric methods cannot predict Doppler at an altitude above 14 KM, which makes to search for introduction of new denoising methods. More research is predominantly done on many denoising algorithms and tested with the simulated signal with various thresholds. It is observed that Lifting wavelets (LWT) with OGS is more effective in denoising the signals. Split, predict, and update are the three phases of lifting transform which on application of these steps reduces noise effectively. The LWT with OGS is applied to MST radar data and the research results shows that the noise level is reduced at higher altitudes and the signal-to-noise ratio is improved.

Improving the BER and PAPR performances of optical OFDM with lazy lifting wavelet transform

Improving the BER and PAPR performances of optical OFDM with lazy lifting wavelet transform

Transient fault extraction for wind turbine generator bearing based on Bayesian biorthogonal sparse representation using adaptive redundant lifting wavelet dictionary

Aiming at the problem that it is difficult to detect effective transient impact characteristics of wind turbine generator bearing fault signals due to non-stationary and strong noise, a fault diagnosis method based on adaptive redundant lifting wavelet dictionary and Bayesian biorthogonal sparse representation (SR) algorithm is proposed. First, a Bayesian model is integrated into the biorthogonal matching pursuit (MP) algorithm to improve the use of dictionary atoms in the effective support set. Then, an adaptive redundant lifting wavelet is used to construct a dictionary matching the transient characteristics of the signal. Finally, the SR algorithm is established by integrating the Bayesian biorthogonal MP model and adaptive redundant lifting wavelet dictionary. Simulation and experimental results show that the proposed method can improve the accuracy of signal reconstruction of transient components and effectively extract bearing fault features, thus verifying the effectiveness and robustness of the method.

Simulation and FPGA Implementation of Transient Power Quality Disturbance Detection

With the access to new energy in the smart grids and the massive use of nonlinear and unbalanced large loads, the problem of power quality becomes more and more serious. At present, the transient power quality disturbance problem has been paid more attention to. The research on transient power quality is relatively late, and various detection methods and technologies are not mature. It is necessary to use more efficient methods to detect and identify transient power quality to improve the safety of electricity use. This paper proposes to detect transient power quality disturbance by wavelet transform. In this paper, the original signal modelling of five kinds of power quality problems such as voltage sag and voltage swell. The 9/7 wavelet lifting coefficient is optimized in this paper and is carried out on the MATLAB software platform to improve the processing speed of the algorithm and realize parallel processing. The simulation results show that the improved lifting wavelet processing can effectively detect the transient power quality disturbance.

Hybrid noise removal to improve the accuracy of inertial sensors using lifting wavelet transform optimized by genetic algorithm

An Inertial Navigation System (INS) is a standalone system that provides continuous navigation information on the position, velocity, and attitude in various conditions. Gyroscopes and accelerometers are essential components of INS. However, these sensors are prone to errors that accumulate over time and degrade the accuracy of the INS. Therefore, enhancing the performance of INS is a challenging problem. This paper aims to address this problem by proposing a method to reduce errors in real-time processing. The method uses Lifting Wavelet Transform (LWT), a popular denoising technique that belongs to the wavelet family and has an advantage over the classic wavelets in terms of time and computation complexity. Moreover, the method employs an optimization technique based on the Genetic algorithm as an intelligent averaging for combining different multi-level LWTs, which significantly improves the accuracy and efficiency of INSs. Finally, a new and implementable structure is introduced for denoising inertial sensors. The results show that the proposed method achieves an 83% and 59% improvement in gyroscope and accelerometer data for dynamic data, compared with raw data. Besides, for static data, there are 71% and 36% improvements in gyroscope and accelerometer data, respectively.

Lifting Wavelet-Assisted EM Joint Estimation and Detection in Cooperative Spectrum Sensing.

Spectrum sensing in Cognitive radio (CR) is a way to improve spectrum utilization by detecting spectral holes to achieve a dynamic allocation of spectrum resources. As it is often difficult to obtain accurate wireless environment information in real-world scenarios, the detection performance is limited. Signal-to-noise ratio (SNR), noise variance, and channel prior occupancy rate are critical parameters in wireless spectrum sensing. However, obtaining these parameter values in advance is challenging in practical scenarios. A lifting wavelet-assisted Expectation-Maximization (EM) joint estimation and detection method is proposed to estimate multiple parameters and achieve full-blind detection, which uses lifting wavelet in noise variance estimation to improve detection probability and convergence speed. Moreover, a stream learning strategy is used in estimating SNR and channel prior occupancy rate to fit the scenario where the SU has mobility. The simulation results demonstrate that the proposed method can achieve comparable detection performance to the semi-blind EM method.

Wavelet lifting method for the numerical solution of micropolar lubrication problem of porous journal bearing

The pivotal aim of this paper is to develop the wavelet lifting method for the numerical solution of the micropolar lubrication problem of porous journal bearings. To ensure the applicability of the proposed method initially, test problems are considered and the numerical findings are presented in figures and tables elucidate that, the proposed method is more efficient and promising with the consumption of lesser computational CPU time. Subsequently, the effect of micropolar fluid on the porous journal bearing is analyzed by solving the corresponding non-dimensional Reynolds equation of the lubrication problem is considered. The obtained results for pressure distribution and load carrying capacity with varied parameters show that the squeeze film pressure and load carrying capacity are significantly increased by the micropolar fluid effect as compared to the Newtonian case.

Multi-aggregation network based on non-separable lifting wavelet for single image deraining

Multi-aggregation network based on non-separable lifting wavelet for single image deraining

An automatic flame detection system for outdoor areas

Traditional fire detection depends on smoke sensors. This strategy, however, is unsuited for big and open buildings, as well as outdoor regions. As a result, based on computer vision systems, this research proposes an effective method for recognizing flames in open areas. To minimize data size without losing important information, integer Haar lifting wavelet transform is used to frame and analyze the input video. Then, three color spaces (binary, hue, saturation, value (HSV), and YCbC) are used in simultaneous color detection. In binary space, Otsu’s approach is utilized to determine automated intensity pixels. Additionally, using frame differences to reduce false alarms. According to the experimental results, the approach achieves 99% accuracy for offline videos and surpasses 93% accuracy for real-time videos while maintaining a lower level of complexity.

Directional lifting wavelet transform for image edge analysis

In this paper, we propose a new two-dimensional directional discrete wavelet transform that can decompose an image into 12 multiscale directional edge components. The proposed transform is designed in a fully discrete setting and thus is easy to implement in actual computations. The proposed transform is viewed as a category of redundant discrete wavelet transforms implemented by fast in-place computational algorithms by a lifting scheme that has been modified to incorporate redundancy. The redundancy is limited to (N×J+1)/4, where N=12 is the directional selectivity and J is a decomposition level of the multiscale transform. Numerical experiments in edge analysis using various images demonstrate the advantages of the proposed method over some conventional standard methods. The proposed method outperforms several conventional edge detection methods in identifying both the location and orientation of edges, and well captures the directional and geometrical features of images.

A multi-image compression and encryption scheme based on fractional chaotic map

In this paper, a visual security encryption scheme for multi-color images based on BP neural network and fractional chaotic map is proposed, which disguises secret images as a meaningful visual image. Firstly, three color images are compressed based on BP neural network. Then, according to the pseudo-random sequence generated by fractional chaotic map, the merged compressed images are scrambled by spiral transformation and diffused by XOR, in which the direction and degree of spiral transformation can be adjusted. In order to ensure the visual effect of the camouflage image, the lifting wavelet transform (LWT) is used to decompose the carrier image to obtain the coefficient matrix, and the cipher images are adjusted to a narrow range and embedded into the coefficient matrixes based on the pseudo-random sequence. Finally, visually secure image can be generated by inverse lifting wavelet transform. The reverse algorithm can restore the images by extraction, decryption and decompression. Experimental results verify that the proposed scheme has feasibility, robustness, anti-noise and clipping capability, and the PSNR value is no less than 31.4 under various attacks.

Novel multi-media steganography model using meta-heuristic and deep learning assisted adaptive lifting wavelet transform

The major goal of this proposal is to implement a new steganography model with multi-media data. Initially, in video steganography and frames are extracted and then, the keyframes with texture and motion features of gathered video are selected through Deep Convolutional Neural Networks (DCNN). Then, the optimal region selection for embedding is carried out using the Improved Artificial Gorilla Troops Optimizer (IAGTO). Secondly, image steganography is performed by collecting the images, where the color channel selection is done through DCNN. Thirdly, audio steganography is performed by gathering the input audios from the standard datasets. Further, the optimal time instant selection is performed by the same IAGTO algorithm, which will be fed to the next phase. Finally, the audio embedding is done by ALWT, and then, the stego audios are extracted by taking inverse ALWT. From the experimental analysis, successful embedding over multi-media data is achieved..

Hybrid domain digital watermarking scheme based on improved differential evolution algorithm and singular value block embedding

AbstractThe internet and related technologies have promoted the development of medical and health fields, especially remote diagnosis. As medical images may be stolen in the transmission process, the patient's personal information could be leaked. Aiming at the problem of privacy disclosure of colour medical images, a hybrid domain watermarking scheme based on improved differential evolution (DE) and the singular value block embedding (SVBE) is proposed in this study. Through this scheme, the image containing the patient's information is hidden in the patient's medical carrier image as a watermark. First, redistributed invariant lifting wavelet transform (RILWT), discrete wavelet transform (DWT), and singular value decomposition (SVD) are used to process the colour medical carrier image, and the high‐frequency information in the integer wavelet domain of the watermark is embedded into the processed carrier image using the proposed singular value block embedding method based on the improved differential evolution algorithm. At the same time, to increase the security of the watermark scheme, a digital signature based on the SHA‐384 hash function is designed for verification before watermark extraction. Compared with recent related research, the scheme has strong invisibility and robustness.