The temporal and genomic scale of selection following hybridization.

Genomic evidence supports an important role for selection in shaping patterns of introgression along the genome, but frameworks for understanding the evolutionary dynamics within hybrid populations that underlie these patterns have been lacking. Due to the clock-like effect of recombination in hybrids breaking up parental haplotypes, drift and selection produce predictable patterns of ancestry variation at varying spatial genomic scales through time. Here, we develop methods based on the Discrete Wavelet Transform to study the genomic scale of local ancestry variation and its association with recombination rates and show that these methods capture temporal dynamics of drift and genome-wide selection after hybridization. We apply these methods to published datasets from hybrid populations of swordtail fish (Xiphophorus) and baboons (Papio) and to inferred Neanderthal introgression in modern humans. Across systems, upward of 20% of variation in local ancestry at the broadest genomic scales can be attributed to systematic selection against introgressed alleles, consistent with strong selection acting on early-generation hybrids. Signatures of selection at fine genomic scales suggest selection over longer time scales; however, we suggest that our ability to confidently infer selection at fine scales is likely limited by inherent biases in current methods for estimating local ancestry from contiguous segments of genomic similarity. Wavelet approaches will become widely applicable as genomic data from systems with introgression become increasingly available and can help shed light on generalities of the genomic consequences of interspecific hybridization.

A multi-frequency approach of the altered functional connectome for autism spectrum disorder identification.

Autism spectrum disorder stands as a multifaceted and heterogeneous neurodevelopmental condition. The utilization of functional magnetic resonance imaging to construct functional brain networks proves instrumental in comprehending the intricate interplay between brain activity and autism spectrum disorder, thereby elucidating the underlying pathogenesis at the cerebral level. Traditional functional brain networks, however, typically confine their examination to connectivity effects within a specific frequency band, disregarding potential connections among brain areas that span different frequency bands. To harness the full potential of interregional connections across diverse frequency bands within the brain, our study endeavors to develop a novel multi-frequency analysis method for constructing a comprehensive functional brain networks that incorporates multiple frequencies. Specifically, our approach involves the initial decomposition of functional magnetic resonance imaging into distinct frequency bands through wavelet transform. Subsequently, Pearson correlation is employed to generate corresponding functional brain networks and kernel for each frequency band. Finally, the classification was performed by a multi-kernel support vector machine, to preserve the connectivity effects within each band and the connectivity patterns shared among the different bands. Our proposed multi-frequency functional brain networks method yielded notable results, achieving an accuracy of 89.1%, a sensitivity of 86.67%, and an area under the curve of 0.942 in a publicly available autism spectrum disorder dataset.

Integration of graph network with kernel SVM and logistic regression for identification of biomarkers in SCA12 and its diagnosis.

Spinocerebellar ataxia type 12 is a hereditary and neurodegenerative illness commonly found in India. However, there is no established noninvasive automatic diagnostic system for its diagnosis and identification of imaging biomarkers. This work proposes a novel four-phase machine learning-based diagnostic framework to find spinocerebellar ataxia type 12 disease-specific atrophic-brain regions and distinguish spinocerebellar ataxia type 12 from healthy using a real structural magnetic resonance imaging dataset. Firstly, each brain region is represented in terms of statistics of coefficients obtained using 3D-discrete wavelet transform. Secondly, a set of relevant regions are selected using a graph network-based method. Thirdly, a kernel support vector machine is used to capture nonlinear relationships among the voxels of a brain region. Finally, the linear relationship among the brain regions is captured to build a decision model to distinguish spinocerebellar ataxia type 12 from healthy by using the regularized logistic regression method. A classification accuracy of 95% and a harmonic mean of precision and recall, i.e. F1-score of 94.92%, is achieved. The proposed framework provides relevant regions responsible for the atrophy. The importance of each region is captured using Shapley Additive exPlanations values. We also performed a statistical analysis to find volumetric changes in spinocerebellar ataxia type 12 group compared to healthy. The promising result of the proposed framework shows that clinicians can use it for early and timely diagnosis of spinocerebellar ataxia type 12.

MarkerDetector: A method for robust fiducial marker detection in electron micrographs using wavelet-based template.

Fiducial marker detection in electron micrographs becomes an important and challenging task with the development of large-field electron microscopy. The fiducial marker detection plays an important role in several steps during the process of electron micrographs, such as the alignment and parameter calibrations. However, limited by the conditions of low signal-to-noise ratio (SNR) in the electron micrographs, the performance of fiducial marker detection is severely affected. In this work, we propose the MarkerDetector, a novel algorithm for detecting fiducial markers in electron micrographs. The proposed MarkerDetector is built upon the following contributions: Firstly, a wavelet-based template generation algorithm is devised in MarkerDetector. By adopting a shape-based criterion, a high-quality template can be obtained. Secondly, a robust marker determination strategy is devised by utilizing statistic-based filtering, which can guarantee the correctness of the detected fiducial markers. The average running time of our algorithm is 1.67 seconds with promising accuracy, indicating its practical feasibility for applications in electron micrographs.

A comparison of wavelet-based action potential detection from the NeuroAmp and the Iowa Bioengineering Nerve Traffic Analysis system.

Microneurographic recordings of muscle sympathetic nerve activity (MSNA) reflect postganglionic sympathetic axonal activity directed toward the skeletal muscle vasculature. Recordings are typically evaluated for spontaneous bursts of MSNA; however, the filtering and integration of raw neurograms to obtain multiunit bursts conceals the underlying c-fiber discharge behavior. The continuous wavelet transform with matched mother wavelet has permitted the assessment of action potential discharge patterns, but this approach uses a mother wavelet optimized for an amplifier that is no longer commercially available (University of Iowa Bioengineering Nerve Traffic Analysis System; Iowa NTA). The aim of this project was to determine the morphology and action potential detection performance of mother wavelets created from the commercially available NeuroAmp (ADinstruments), from distinct laboratories, compared with a mother wavelet generated from the Iowa NTA. Four optimized mother wavelets were generated in a two-phase iterative process from independent datasets, collected by separate laboratories (one Iowa NTA, three NeuroAmp). Action potential extraction performance of each mother wavelet was compared for each of the NeuroAmp-based datasets. The total number of detected action potentials was not significantly different across wavelets. However, the predictive value of action potential detection was reduced when the Iowa NTA wavelet was used to detect action potentials in NeuroAmp data, but not different across NeuroAmp wavelets. To standardize approaches, we recommend a NeuroAmp-optimized mother wavelet be used for the evaluation of sympathetic action potential discharge behavior when microneurographic data are collected with this system.NEW & NOTEWORTHY The morphology of custom mother wavelets produced across laboratories using the NeuroAmp was highly similar, but distinct from the University of Iowa Bioengineering Nerve Traffic Analysis System. Although the number of action potentials detected was similar between collection systems and mother wavelets, the predictive value differed. Our data suggest action potential analysis using the continuous wavelet transform requires a mother wavelet optimized for the collection system.

Quantifying local field potential dynamics with amplitude and frequency stability between ON and OFF medication and stimulation in Parkinson's disease.

Neural oscillations are critical to understanding the synchronisation of neural activities and their relevance to neurological disorders. For instance, the amplitude of beta oscillations in the subthalamic nucleus has gained extensive attention, as it has been found to correlate with medication status and the therapeutic effects of continuous deep brain stimulation in people with Parkinson's disease. However, the frequency stability of subthalamic nucleus beta oscillations, which has been suggested to be associated with dopaminergic information in brain states, has not been well explored. Moreover, the administration of medicine can have inverse effects on changes in frequency and amplitude. In this study, we proposed a method based on the stationary wavelet transform to quantify the amplitude and frequency stability of subthalamic nucleus beta oscillations and evaluated the method using simulation and real data for Parkinson's disease patients. The results suggest that the amplitude and frequency stability quantification has enhanced sensitivity in distinguishing pathological conditions in Parkinson's disease patients. Our quantification shows the benefit of combining frequency stability information with amplitude and provides a new potential feedback signal for adaptive deep brain stimulation.

Multiresolution Analysis of HRRR Meteorological Parameters and GOES-R AOD for Hourly PM2.5 Prediction.

High-resolution, comprehensive exposure data are crucial for accurately estimating the human health impact of PM2.5. In recent years, satellite remote sensing data have been increasingly utilized in PM2.5 models to overcome the limited spatial coverage of ground monitoring stations. However, data gaps in satellite-retrieved parameters such as aerosol optical depth (AOD), the sparsity of regulatory air quality monitors for model training, and nonlinear relationships between PM2.5 and meteorological conditions can affect model performance and cause data gaps in most existing PM2.5 models. In this study, spatial gaps in AOD obtained from Geostationary Operational Environmental Satellite-16 are filled using Goddard Earth Observing System Composition Forecasting AOD estimations. Furthermore, to improve model performance, meteorological predictors such as temperature from the High-Resolution Rapid Refresh model are preprocessed using Daubechies wavelet to extract low and high frequency components. The spatially gap-filled AOD, along with meteorological data, are ingested into a machine learning model to predict hourly PM2.5 at a 1 km spatial resolution in California. The model evaluation metrics (OOB (out-of-bag) R2 = 0.86 and RMSE (root-mean-square error) = 9.27 µg/m3 and 10-fold spatial cross-validation R2 = 0.82 and RMSE = 9.82 µg/m3) demonstrate the model's reliability in predicting ambient PM2.5, especially for states like California that experience frequent episodes of wildfires.

Identification of Methamphetamine Abusers Can Be Supported by EEG-Based Wavelet Transform and BiLSTM Networks.

Methamphetamine (MA) is a neurological drug, which is harmful to the overall brain cognitive function when abused. Based on this property of MA, people can be divided into those with MA abuse and healthy people. However, few studies to date have investigated automatic detection of MA abusers based on the neural activity. For this reason, the purpose of this research was to investigate the difference in the neural activity between MA abusers and healthy persons and accordingly discriminate MA abusers. First, we performed event-related potential (ERP) analysis to determine the time range of P300. Then, the wavelet coefficients of the P300 component were extracted as the main features, along with the time and frequency domain features within the selected P300 range to classify. To optimize the feature set, F_score was used to remove features below the average score. Finally, a Bidirectional Long Short-term Memory (BiLSTM) network was performed for classification. The experimental result showed that the detection accuracy of BiLSTM could reach 83.85%. In conclusion, the P300 component of EEG signals of MA abusers is different from that in normal persons. Based on this difference, this study proposes a novel way for the prevention and diagnosis of MA abuse.

Wavelet transform-based frequency self-adaptive model for functional brain network.

The accurate estimation of functional brain networks is essential for comprehending the intricate relationships between different brain regions. Conventional methods such as Pearson Correlation and Sparse Representation often fail to uncover concealed information within diverse frequency bands. To address this limitation, we introduce a novel frequency-adaptive model based on wavelet transform, enabling selective capture of highly correlated frequency band sequences. Our approach involves decomposing the original time-domain signal from resting-state functional magnetic resonance imaging into distinct frequency domains, thus constructing an adjacency matrix that offers enhanced separation of features across brain regions. Comparative analysis demonstrates the superior performance of our proposed model over conventional techniques, showcasing improved clarity and distinctiveness. Notably, we achieved the highest accuracy rate of 89.01% using Sparse Representation based on Wavelet Transform, outperforming Pearson Correlation based on Wavelet Transform with an accuracy of 81.32%. Importantly, our method optimizes raw data without significantly altering feature topology, rendering it adaptable to various functional brain network estimation approaches. Overall, this innovation holds the potential to advance the understanding of brain function and furnish more accurate samples for future research and clinical applications.

Deep demosaicking convolution neural network and quantum wavelet transform-based image denoising.

Demosaicking is a popular scientific area that is being explored by a vast number of scientists. Current digital imaging technologies capture colour images with a single monochrome sensor. In addition, the colour images were captured using a sensor coupled with a Colour Filter Array (CFA). Furthermore, the demosaicking procedure is required to obtain a full-colour image. Image denoising and image demosaicking are the two important image restoration techniques, which have increased popularity in recent years. Finding a suitable strategy for multiple image restoration is critical for researchers. Hence, a deep learning (DL) based image denoising and image demosaicking is developed in this research. Moreover, the Autoregressive Circle Wave Optimization (ACWO) based Demosaicking Convolutional Neural Network (DMCNN) is designed for image demosaicking. The Quantum Wavelet Transform (QWT) is used in the image denoising process. Similarly, Quantum Wavelet Transform (QWT) is used to analyse the abrupt changes in the input image with noise. The transformed image is then subjected to a thresholding technique, which determines an appropriate threshold range. Once the threshold range has been determined, soft thresholding is applied to the resulting wavelet coefficients. After that, the extraction and reconstruction of the original image is carried out using the Inverse Quantum Wavelet Transform (IQWT). Finally, the fused image is created by combining the results of both processes using a weighted average. The denoised and demosaicked images are combined using the weighted average technique. Furthermore, the proposed QWT+DMCNN-ACWO model provided the ideal values of Peak signal-to-noise ratio (PSNR), Second derivative like measure of enhancement (SDME), Structural Similarity Index (SSIM), Figure of Merit (FOM) of 0.890, and computational time of 49.549 dB, 59.53 dB, 0.963, 0.890, and 0.571, respectively.

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

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.

Detection of Marchiafava Bignami disease using distinct deep learning techniques in medical diagnostics.

PURPOSE: To detect the Marchiafava Bignami Disease (MBD) using a distinct deep learning technique. BACKGROUND: Advanced deep learning methods are becoming more crucial in contemporary medical diagnostics, particularly for detecting intricate and uncommon neurological illnesses such as MBD. This rare neurodegenerative disorder, sometimes associated with persistent alcoholism, is characterized by the loss of myelin or tissue death in the corpus callosum. It poses significant diagnostic difficulties owing to its infrequency and the subtle signs it exhibits in its first stages, both clinically and on radiological scans. METHODS: The novel method of Variational Autoencoders (VAEs) in conjunction with attention mechanisms is used to identify MBD peculiar diseases accurately. VAEs are well-known for their proficiency in unsupervised learning and anomaly detection. They excel at analyzing extensive brain imaging datasets to uncover subtle patterns and abnormalities that traditional diagnostic approaches may overlook, especially those related to specific diseases. The use of attention mechanisms enhances this technique, enabling the model to concentrate on the most crucial elements of the imaging data, similar to the discerning observation of a skilled radiologist. Thus, we utilized the VAE with attention mechanisms in this study to detect MBD. Such a combination enables the prompt identification of MBD and assists in formulating more customized and efficient treatment strategies. RESULTS: A significant breakthrough in this field is the creation of a VAE equipped with attention mechanisms, which has shown outstanding performance by achieving accuracy rates of over 90% in accurately differentiating MBD from other neurodegenerative disorders. CONCLUSION: This model, which underwent training using a diverse range of MRI images, has shown a notable level of sensitivity and specificity, significantly minimizing the frequency of false positive results and strengthening the confidence and dependability of these sophisticated automated diagnostic tools.

Optimized deep CNN for detection and classification of diabetic retinopathy and diabetic macular edema.

Diabetic Retinopathy (DR) and Diabetic Macular Edema (DME) are vision related complications prominently found in diabetic patients. The early identification of DR/DME grades facilitates the devising of an appropriate treatment plan, which ultimately prevents the probability of visual impairment in more than 90% of diabetic patients. Thereby, an automatic DR/DME grade detection approach is proposed in this work by utilizing image processing. In this work, the retinal fundus image provided as input is pre-processed using Discrete Wavelet Transform (DWT) with the aim of enhancing its visual quality. The precise detection of DR/DME is supported further with the application of suitable Artificial Neural Network (ANN) based segmentation technique. The segmented images are subsequently subjected to feature extraction using Adaptive Gabor Filter (AGF) and the feature selection using Random Forest (RF) technique. The former has excellent retinal vein recognition capability, while the latter has exceptional generalization capability. The RF approach also assists with the improvement of classification accuracy of Deep Convolutional Neural Network (CNN) classifier. Moreover, Chicken Swarm Algorithm (CSA) is used for further enhancing the classifier performance by optimizing the weights of both convolution and fully connected layer. The entire approach is validated for its accuracy in determination of grades of DR/DME using MATLAB software. The proposed DR/DME grade detection approach displays an excellent accuracy of 97.91%.

Wavelet Transforms Significantly Sparsify and Compress Tactile Interactions.

As higher spatiotemporal resolution tactile sensing systems are being developed for prosthetics, wearables, and other biomedical applications, they demand faster sampling rates and generate larger data streams. Sparsifying transformations can alleviate these requirements by enabling compressive sampling and efficient data storage through compression. However, research on the best sparsifying transforms for tactile interactions is lagging. In this work we construct a library of orthogonal and biorthogonal wavelet transforms as sparsifying transforms for tactile interactions and compare their tradeoffs in compression and sparsity. We tested the sparsifying transforms on a publicly available high-density tactile object grasping dataset (548 sensor tactile glove, grasping 26 objects). In addition, we investigated which dimension wavelet transform-1D, 2D, or 3D-would best compress these tactile interactions. Our results show that wavelet transforms are highly efficient at compressing tactile data and can lead to very sparse and compact tactile representations. Additionally, our results show that 1D transforms achieve the sparsest representations, followed by 3D, and lastly 2D. Overall, the best wavelet for coarse approximation is Symlets 4 evaluated temporally which can sparsify to 0.5% sparsity and compress 10-bit tactile data to an average of 0.04 bits per pixel. Future studies can leverage the results of this paper to assist in the compressive sampling of large tactile arrays and free up computational resources for real-time processing on computationally constrained mobile platforms like neuroprosthetics.

Signal Separation Operator Based on Wavelet Transform for Non-Stationary Signal Decomposition.

This paper develops a new frame for non-stationary signal separation, which is a combination of wavelet transform, clustering strategy and local maximum approximation. We provide a rigorous mathematical theoretical analysis and prove that the proposed algorithm can estimate instantaneous frequencies and sub-signal modes from a blind source signal. The error bounds for instantaneous frequency estimation and sub-signal recovery are provided. Numerical experiments on synthetic and real data demonstrate the effectiveness and efficiency of the proposed algorithm. Our method based on wavelet transform can be extended to other time-frequency transforms, which provides a new perspective of time-frequency analysis tools in solving the non-stationary signal separation problem.

Multibranch Wavelet-Based Network for Image Demoiréing.

Moiré patterns caused by aliasing between the camera's sensor and the monitor can severely degrade image quality. Image demoiréing is a multi-task image restoration method that includes texture and color restoration. This paper proposes a new multibranch wavelet-based image demoiréing network (MBWDN) for moiré pattern removal. Moiré images are separated into sub-band images using wavelet decomposition, and demoiréing can be achieved using the different learning strategies of two networks: moiré removal network (MRN) and detail-enhanced moiré removal network (DMRN). MRN removes moiré patterns from low-frequency images while preserving the structure of smooth areas. DMRN simultaneously removes high-frequency moiré patterns and enhances fine details in images. Wavelet decomposition is used to replace traditional upsampling, and max pooling effectively increases the receptive field of the network without losing the spatial information. Through decomposing the moiré image into different levels using wavelet transform, the feature learning results of each branch can be fully preserved and fed into the next branch; therefore, possible distortions in the recovered image are avoided. Thanks to the separation of high- and low-frequency images during feature training, the proposed two networks achieve impressive moiré removal effects. Based on extensive experiments conducted using public datasets, the proposed method shows good demoiréing validity both quantitatively and qualitatively when compared with the state-of-the-art approaches.

A Robust Deep Feature Extraction Method for Human Activity Recognition Using a Wavelet Based Spectral Visualisation Technique.

Human Activity Recognition (HAR), alongside Ambient Assisted Living (AAL), are integral components of smart homes, sports, surveillance, and investigation activities. To recognize daily activities, researchers are focusing on lightweight, cost-effective, wearable sensor-based technologies as traditional vision-based technologies lack elderly privacy, a fundamental right of every human. However, it is challenging to extract potential features from 1D multi-sensor data. Thus, this research focuses on extracting distinguishable patterns and deep features from spectral images by time-frequency-domain analysis of 1D multi-sensor data. Wearable sensor data, particularly accelerator and gyroscope data, act as input signals of different daily activities, and provide potential information using time-frequency analysis. This potential time series information is mapped into spectral images through a process called use of 'scalograms', derived from the continuous wavelet transform. The deep activity features are extracted from the activity image using deep learning models such as CNN, MobileNetV3, ResNet, and GoogleNet and subsequently classified using a conventional classifier. To validate the proposed model, SisFall and PAMAP2 benchmark datasets are used. Based on the experimental results, this proposed model shows the optimal performance for activity recognition obtaining an accuracy of 98.4% for SisFall and 98.1% for PAMAP2, using Morlet as the mother wavelet with ResNet-101 and a softmax classifier, and outperforms state-of-the-art algorithms.

Mechanism-Based Fault Diagnosis Deep Learning Method for Permanent Magnet Synchronous Motor.

As an important driving device, the permanent magnet synchronous motor (PMSM) plays a critical role in modern industrial fields. Given the harsh working environment, research into accurate PMSM fault diagnosis methods is of practical significance. Time-frequency analysis captures the rich features of PMSM operating conditions, and convolutional neural networks (CNNs) offer excellent feature extraction capabilities. This study proposes an intelligent fault diagnosis method based on continuous wavelet transform (CWT) and CNNs. Initially, a mechanism analysis is conducted on the inter-turn short-circuit and demagnetization faults of PMSMs, identifying and displaying the key feature frequency range in a time-frequency format. Subsequently, a CNN model is developed to extract and classify these time-frequency images. The feature extraction and diagnosis results are visualized with t-distributed stochastic neighbor embedding (t-SNE). The results demonstrate that our method achieves an accuracy rate of over 98.6% for inter-turn short-circuit and demagnetization faults in PMSMs of various severities.

DCFNet: Infrared and Visible Image Fusion Network Based on Discrete Wavelet Transform and Convolutional Neural Network.

Aiming to address the issues of missing detailed information, the blurring of significant target information, and poor visual effects in current image fusion algorithms, this paper proposes an infrared and visible-light image fusion algorithm based on discrete wavelet transform and convolutional neural networks. Our backbone network is an autoencoder. A DWT layer is embedded in the encoder to optimize frequency-domain feature extraction and prevent information loss, and a bottleneck residual block and a coordinate attention mechanism are introduced to enhance the ability to capture and characterize the low- and high-frequency feature information; an IDWT layer is embedded in the decoder to achieve the feature reconstruction of the fused frequencies; the fusion strategy adopts the l1-norm fusion strategy to integrate the encoder's output frequency mapping features; a weighted loss containing pixel loss, gradient loss, and structural loss is constructed for optimizing network training. DWT decomposes the image into sub-bands at different scales, including low-frequency sub-bands and high-frequency sub-bands. The low-frequency sub-bands contain the structural information of the image, which corresponds to the important target information, while the high-frequency sub-bands contain the detail information, such as edge and texture information. Through IDWT, the low-frequency sub-bands that contain important target information are synthesized with the high-frequency sub-bands that enhance the details, ensuring that the important target information and texture details are clearly visible in the reconstructed image. The whole process is able to reconstruct the information of different frequency sub-bands back into the image non-destructively, so that the fused image appears natural and harmonious visually. Experimental results on public datasets show that the fusion algorithm performs well according to both subjective and objective evaluation criteria and that the fused image is clearer and contains more scene information, which verifies the effectiveness of the algorithm, and the results of the generalization experiments also show that our network has good generalization ability.

An Improved U-Net Infrared Small Target Detection Algorithm Based on Multi-Scale Feature Decomposition and Fusion and Attention Mechanism.

Infrared small target detection technology plays a crucial role in various fields such as military reconnaissance, power patrol, medical diagnosis, and security. The advancement of deep learning has led to the success of convolutional neural networks in target segmentation. However, due to challenges like small target scales, weak signals, and strong background interference in infrared images, convolutional neural networks often face issues like leakage and misdetection in small target segmentation tasks. To address this, an enhanced U-Net method called MST-UNet is proposed, the method combines multi-scale feature decomposition and fusion and attention mechanisms. The method involves using Haar wavelet transform instead of maximum pooling for downsampling in the encoder to minimize feature loss and enhance feature utilization. Additionally, a multi-scale residual unit is introduced to extract contextual information at different scales, improving sensory field and feature expression. The inclusion of a triple attention mechanism in the encoder structure further enhances multidimensional information utilization and feature recovery by the decoder. Experimental analysis on the NUDT-SIRST dataset demonstrates that the proposed method significantly improves target contour accuracy and segmentation precision, achieving IoU and nIoU values of 80.09% and 80.19%, respectively.