Background Noise Interference Research Articles

Highly Conductive and Sensitive Wearable Strain Sensors with Metal/Nanoparticle Double Layer for Noninterference Voice Detection.

Human voice recognition via skin-attachable devices has significant potential for gathering important physiological information from acoustic data without background noise interference. In this study, a highly sensitive and conductive wearable crack-based strain sensor was developed for voice-recognition systems. The sensor was fabricated using a double-layer structure of Ag nanoparticles (NPs) and Ag metal on a biocompatible polydimethylsiloxane substrate. The top metal layer acts as a conducting active layer, whereas the bottom Ag NP layer induces channel cracks in the upper layer, effectively hindering current flow. Subsequently, the double-layer film exhibits a low electrical resistance value (<5 × 10-5 Ω cm), ultrahigh sensitivity (gauge factor = 1870), and a fast response/recovery time (252/168 μs). A sound wave was detected at a high frequency of 15 kHz with a signal-to-noise ratio (SNR) over 40 dB. The sensor exhibited excellent anti-interference characteristics and effectively differentiated between different voice qualities (modal, pressed, and breathy), with a systematic analysis revealing successful detection of the laryngeal state and glottal source. This ultrasensitive wearable sensor has potential applications in various physiological signal measurement methods, personalized healthcare systems, and ubiquitous computing.

LPMSNet: Location Pooling Multi-Scale Network for Cloud and Cloud Shadow Segmentation

Among the most difficult difficulties in contemporary satellite image-processing subjects is cloud and cloud shade segmentation. Due to substantial background noise interference, existing cloud and cloud shadow segmentation techniques would result in false detection and missing detection. We propose a Location Pooling Multi-Scale Network (LPMSNet) in this study. The residual network is utilised as the backbone in this method to acquire semantic info on various levels. Simultaneously, the Location Attention Multi-Scale Aggregation Module (LAMA) is introduced to obtain the image’s multi-scale info. The Channel Spatial Attention Module (CSA) is introduced to boost the network’s focus on segmentation goals. Finally, in view of the problem that the edge details of cloud as well as cloud shade are easily lost, this work designs the Scale Fusion Restoration Module (SFR). SFR can perform picture upsampling as well as the acquisition of edge detail information from cloud as well as cloud shade. The mean intersection over union (MIoU) accuracy of this network reached 94.36% and 81.60% on the Cloud and Cloud Shadow Dataset and the five-category dataset L8SPARCS, respectively. On the two-category HRC-WHU Dataset, the accuracy of the network on the intersection over union (IoU) reached 90.51%. In addition, in the Cloud and Cloud Shadow Dataset, our network achieves 97.17%, 96.83%, and 97.00% in precision (P), recall (R), and F1 score (F1) in cloud segmentation tasks, respectively. In the cloud shadow segmentation task, precision (P), recall (R), and F1 score (F1) reached 95.70%, 96.38%, and 96.04%, respectively. Therefore, this method has a significant advantage over the current cloud and cloud shade segmentation methods.

A double transformer residual super-resolution network for cross-resolution person re-identification

Cross-resolution person re-identification is a challenging problem in the field of person re-identification. In order to solve the problem of resolution mismatch, many studies introduce super-resolution into person re-identification tasks. In this work, we propose a cross-resolution person re-identification method based on double transformer residual super-resolution network (DTRSR), which mainly includes super-resolution module and person re-identification module. In the super-resolution module, we propose the double transformer network as our attention module. First of all, we divide the features extracted by the residual network. Then calculate the similarity between each local feature and the global feature after average pooling and maximum pooling respectively, which makes our module quickly capture the hidden weight information in the spatial domain. In the person re-identification module, we propose an effective fusion method based on key point features (KPFF). The key point extraction model can not only solve the problem that local features can not be accurately aligned, but also remove the interference of background noise. In order to fully mine the relationship between the features of each key point, we calculate the two-way correlation between each key point feature and other features, and then superimpose the two-way correlation with the feature itself to get the superposition feature which contains global and local information. The effectiveness of this method is proved by extensive experiments. Compared with the most advanced methods, the test results in the three datasets show that our method improves rank-1 by 1.1%, 3.5% and 1.7%; and rank-5 by 1.3%, 1.7% and 0.3%; and rank-10 by 0.1%, 0.4% and 0.1%, respectively.

Printing roller image salient object detection based on multi-scale feature fusion

In this study, aiming at the problem that the surface defect image of the printing roller has different sizes and a large number of defects, a salient object detection method based on stepwise multi-scale feature fusion is proposed, which consists of a stepwise multi-scale feature guidance module, a multi-resolution information fusion module, and a deeply supervised side output. Specifically, the stepwise multi-scale feature guidance module contains two paths, top-down and bottom-up, which strengthen the transmission of multi-scale features in the network, and fuse multi-level features through the multi-resolution information fusion module to suppress the interference of background noise and redundant features. In addition, deeply supervised side outputs are used to eliminate differences caused by background and foreground imbalance. The experimental results on the roller surface defect dataset show that the method can achieve Fmax, MAE of 0.7959, 0.0144, and the detection rate can reach 24.98fps, which has better detection performance than other algorithms.

MU-Net: Embedding MixFormer into Unet to Extract Water Bodies from Remote Sensing Images

Water bodies extraction is important in water resource utilization and flood prevention and mitigation. Remote sensing images contain rich information, but due to the complex spatial background features and noise interference, problems such as inaccurate tributary extraction and inaccurate segmentation occur when extracting water bodies. Recently, using a convolutional neural network (CNN) to extract water bodies is gradually becoming popular. However, the local property of CNN limits the extraction of global information, while Transformer, using a self-attention mechanism, has great potential in modeling global information. This paper proposes the MU-Net, a hybrid MixFormer architecture, as a novel method for automatically extracting water bodies. First, the MixFormer block is embedded into Unet. The combination of CNN and MixFormer is used to model the local spatial detail information and global contextual information of the image to improve the ability of the network to capture semantic features of the water body. Then, the features generated by the encoder are refined by the attention mechanism module to suppress the interference of image background noise and non-water body features, which further improves the accuracy of water body extraction. The experiments show that our method has higher segmentation accuracy and robust performance compared with the mainstream CNN- and Transformer-based semantic segmentation networks. The proposed MU-Net achieves 90.25% and 76.52% IoU on the GID and LoveDA datasets, respectively. The experimental results also validate the potential of MixFormer in water extraction studies.

Weak Fault Feature Extraction for Rolling Element Bearing Based on a Two-Stage Method

Timely and effective feature extraction is the key for fault diagnosis of rolling element bearing (REB). However, fault feature extraction will become very difficult in the early weak fault stage of REB due to the interference of strong background noise. To solve the above difficulty, a two-stage feature extraction method for early weak fault of REB is proposed, which mainly combines feature mode decomposition (FMD) with a blind deconvolution (BD) method. Firstly, based on the impulsiveness and cyclostationary characteristics of the vibration signal of faulty REB, FMD is used to decompose the complex original vibration signal into several modes containing single component. Subsequently, the sparse index (SI) is calculated for each mode, and the mode containing sensitive fault feature is selected for further analysis. Subsequently, apply the deconvolution method on the selected mode for further enhancing the impulsive characteristic. At last, traditional envelope spectrum (ES) analysis is applied on the filtered signal, and satisfactory fault features are extracted. Effectiveness and advantages of the proposed method are verified through experimental and engineering signals of REBs.

Deep time–frequency learning for interpretable weak signal enhancement of rotating machineries

Rotating machinery generates periodic impulses when weak faults occur, but the fault resonant bands (FRB) which contains rich fault information is usually seriously contaminated by random interference and background noise. With the development of deep learning (DL), the existing signal enhancement methods based on DL have the property of ”black box”, i.e., limited interpretability, by which the fault components with clear physical meaning (CPM) cannot be extracted. Aiming at the aforementioned problems, an interpretable weak signal enhancement method based on deep time–frequency learning (DTFL) is proposed. Firstly, a series of simulated template signals of different resonant bands with CPM are constructed as training samples for DTFL, besides, a resonant band time–frequency ratio mask with CPM is generated as the training target by using the time–frequency representations (TFR) of pure and noise-added simulated template signals to construct a non-linear mapping relationship between the TFR of simulated template signals and resonant bands, thereby to achieve accurate enhancement of FRB and credible mask suppression of background noise interference. Therefore, the time–frequency ratio mask with CPM obtained from the DTFL model can be adapted to enhance the FRB, which enables the results of the enhanced FRB to be interpretable, thereby the constructed DTFL model is interpretable. The DTFL method overcomes the problem that the existing signal enhancement methods rely heavily on expert experience, which can provide a CPM of the FRB to support the diagnosis of weak faults in rotating machineries.

An enhanced empirical Fourier decomposition method for bearing fault diagnosis

To address the problem that bearing fault signals are usually contaminated by strong background interference due to multiple structures and complex transmission paths, which affects accurate fault feature extraction, an enhanced empirical Fourier decomposition technique was proposed in this paper. First, in order to weaken the influence of transmission path, the trend-line-extraction-based method was utilized in advance, which suppressed the signal distortion and background noise interference. Then, to achieve the appropriate parameter for the empirical Fourier decomposition, the correlation-coefficient-based decomposition number selection approach was constructed to avoid the existence of irrelevant modal functions. The band improvement strategy was proposed to reduce the invalid frequency bands with too narrow bandwidth during the decomposition process, the weighted harmonics significant index was utilized as the target, and the optimal modal components were also determined. Last, the fast Fourier transform was employed, and the bearing fault signatures were accurately detected. The simulation and experimental bearing fault signals were used for analysis; with the help of some comparisons, the analyzed results show that this method can effectively extract the fault characteristics of rolling element bearing from strong background interference.

Identifying Core Wavelengths of Oil Tree’s Hyperspectral Data by Taylor Expansion

The interference of background noise leads to the extremely high spatial complexity of hyperspectral data. Sensitive band selecting is an important task to minimize or eliminate the influence of non-target elements. In this study, Taylor expansion is innovatively used to identify core wavelengths/bands of hyperspectral data. Unlike other traditional methods, this proposed Taylor-CC method considers more local and global information of spectral function to estimate the linear/nonlinear correlation between two wavelengths. Using samples of hyperspectral data with a wavelength range of 350–2500 nm and SPAD for Camellia oleifera, this Taylor-CC method is compared with the traditional PCC method derived from the Pearson correlation coefficient. Using the 240 samples with their different 57 core wavelengths identified by the Taylor-CC method and PCC method, three machine models (i.e., random forest-RF, linear regression-LR, and artificial neural network-ANN) are trained to compare their performances. Their results show that the correlation matrix from the Taylor-CC method represents a clear diagonal pattern with near zero values at most locations away from the diagonal, and all three models confirm that the Taylor-CC method is superior to the PCC method. Moreover, the SPAD spectral response relationship based on machine learning algorithms is constructed, and ANN is the best prediction performance among the three models when using the core wavelengths identified by the Taylor-CC method. The Taylor-CC method proposed in this study not only lays a mathematical foundation for the next analysis of the response mechanism between spectral characteristics and nutrient content of Camellia leaf, but also provides a new idea for the correlation analysis of adjacent spectral bands for hyperspectral signals in many applications.

Study on Fault Feature Extraction of Rolling Bearing Based on Improved WOA-FMD Algorithm

The vibration signal of rolling bearing fault is nonlinear and nonstationary under the interference of background noise, and it is difficult to extract fault features from it. When feature mode decomposition is used to analyze signals, prior parameter settings can easily affect the decomposition results. Therefore, a fault feature extraction method based on improved whale optimization algorithm is proposed to optimize feature modal decomposition parameters. The improved WOA integrates Lévy flight and adaptive weight, and envelope entropy is used as fitness function to optimize feature modal decomposition parameters. The feature mode decomposition of the original signal is performed using the optimal combination of parameters to obtain multiple IMF components. The optimal IMF component envelope demodulation analysis is selected according to the kurtosis value, and the fault feature is extracted through the envelope spectrum. Comparing the LMWOA method with PSO and WOA methods by simulated and experimental signals, the results show that the optimization speed of LMWOA is faster than that of other methods. Compared with CEEMD, VMD, and FMD methods, the improved WOA-FMD method has higher fault feature ratio and can accurately extract fault features under noise interference. This method can effectively solve the parameter adaptive ability and improve the accuracy of fault diagnosis, which has practical significance.

CNTR-YOLO: Improved YOLOv5 Based on ConvNext and Transformer for Aircraft Detection in Remote Sensing Images

Aircraft detection in remote sensing images is an important branch of target detection due to the military value of aircraft. However, the diverse categories of aircraft and the intricate background of remote sensing images often lead to insufficient detection accuracy. Here, we present the CNTR-YOLO algorithm based on YOLOv5 as a solution to this issue. The CNTR-YOLO algorithm improves detection accuracy through three primary strategies. (1) We deploy DenseNet in the backbone to address the vanishing gradient problem during training and enhance the extraction of fundamental information. (2) The CBAM attention mechanism is integrated into the neck to minimize background noise interference. (3) The C3CNTR module is designed based on ConvNext and Transformer to clarify the target’s position in the feature map from both local and global perspectives. This module is applied before the prediction head to optimize the accuracy of prediction results. Our proposed algorithm is validated on the MAR20 and DOTA datasets. The results on the MAR20 dataset show that the mean average precision (mAP) of CNTR-YOLO reached 70.1%, which is a 3.3% improvement compared with YOLOv5l. On the DOTA dataset, the results indicate that the mAP of CNTR-YOLO reached 63.7%, which is 2.5% higher than YOLOv5l.

SVMD coupled with dual-threshold criteria of correlation coefficient: A self-adaptive denoising method for ship-radiated noise signal

Due to the complexity of the marine environment, ship-radiated noise signal (SRNS) often contains harsh marine background noise. Hence extracting the features of SRNS becomes very difficult. Aim to eliminate the interference of background noise, this paper proposes a self-adaptive denoising method for SRNS, called SVMD-Dual-CC-WST, which not only uses the successive variational mode decomposition (SVMD) as a theoretical basis but also combines with the dual-threshold screening of the correlation coefficient (Dual-CC) criterion and wavelet soft threshold (WST). Firstly, different original signals are decomposed into several intrinsic mode functions (IMFs) by SVMD. Then, the CC of the IMFs is calculated, and the IMFs are adaptively divided into three categories using the Dual-CC criterion, including signal IMFs, noisy IMFs, and noise IMFs. Finally, the noise IMFs are discarded, and the noisy IMFs are denoised with WST and then reconstructed with the signal IMFs to obtain the denoising signals. Simulated signals and SRNS experiments prove the effectiveness of the proposed method.

VISUAL ASSESSMENT OF KOROTKOFF SOUNDS FURTHER IMPROVES THE ACCURACY OF A VALIDATED PROFESSIONAL AUTOMATED AUSCULTATORY BLOOD PRESSURE MONITOR – INBODY BPBIO480KV

Objective: A novel automated auscultatory upper-arm cuff blood pressure (BP) monitor for office use (InBody BPBIO480KV, Seoul, S Korea) has been recently validated, which allows healthcare professionals to visually review the Korotkoff sounds curves generated for each BP reading. This study investigated whether this feature could further improve the accuracy of the device by identifying unreliable BP readings. Design and method: Three observers assessed independently the morphology of Korotkoff sound curves generated during a validation study according to the ISO 81060-2:2018 standard, and classified them as having good, fair, or poor signal quality (low signal amplitude or sound intensity, aberrant signal morphology, interference of background noise or other signal artifact, presence of auscultatory gap, or irregular rhythm), separately for the systolic and diastolic BP area. The observers were blinded to the automated and the reference BP measurement results. Disagreement among observers was resolved by a supervisor. Factors associated with poor quality signal were also investigated. Results: A total of 255 Korotkoff sound curves (test BP readings) by 85 participants (mean age 57.3±15.0 years, 53 men) were analyzed. For systolic BP, 82.0/12.2/7.5% were classified as good/fair/poor quality and for diastolic 76.9/12.2/11.0%. Inter-observer agreement in detecting poor quality curves was 84.7/83.1% (systolic/diastolic). Of poor quality curves 10.5/60.7% (systolic/diastolic) clustered in the same individuals. Young age and female sex increased the odds for poor quality signal. ISO validation Criterion 1 (mean BP difference ±SD) was satisfied for readings with good (0.1±4.9/0.3±3.8 mmHg, systolic/diastolic) and fair (-0.4±6.4/0.2±5.0) quality curves, good/fair quality curves (0.1±5.1/0.2±4.0 mmHg, systolic/diastolic), but not for those with poor quality signal (2.7±8.8/3.6±8.1 mmHg). In the ISO validation study, excluding readings with poor quality signal (systolic and/or diastolic area; 40 of 255) Criterion 1 was improved (0.2±4.9/0.2±3.9 mmHg versus 0.3±5.5/0.6±4.7 mmHg). Conclusions: The visual assessment of Korotkoff sounds generated by automated auscultatory BP measurement using the InBody BPBIO480KV professional office BP monitor is useful in identifying unreliable readings and further improves the device accuracy.

Fault Traveling Wave Detection Method based on ICEEMDAN-MCKD

To address the challenge of calibrating the traveling wave-front for fault location in high noise environments, we propose an improved method that combines the ICEEMDAN and maximum correlation kurtosis deconvolution (MCKD). Our approach first decomposes the fault traveling wave signal into modal components using the ICEEMDAN algorithm. Next, the MCKD algorithm enhances the energy amplitude of the decomposed signal, suppresses strong background noise interference, and accurately calibrates the fault traveling wave-front. Simulation results demonstrate that ICEEMDAN-MCKD achieves precise calibration of the wave-front, exhibits strong denoising ability, and performs better than existing methods in terms of detecting traveling waves and minimizing wave-front determination time errors in noisy environments.

IPP: A Seismic P-Wave’s Detection Method Based on the Initial Power of the P-Wave

ABSTRACT The detection of P-wave is essential for the earthquake early warning system. How to detect the P-wave under noise circumstance accurately and rapidly is a challenge work. Based on the relative power of the seismic signal, a new parameter, the initial power of the P-wave (IPP), is proposed to detect the P-wave. By using the relative power of the seismic signal, the interference of the background noise is eliminated, and the initial power of the P-wave and sigma criterion are both applied to detect the P-wave. Through simulation analysis and example tests whose magnitudes are varied from Ms4.0 to Ms8.0, both the misjudgment and the missing rate of the IPP method are 0, and the time deviation within 0.2 s can reach 78.95%. Comparing with the STA/LTA, STP/LTP and PhaseNet methods, the IPP method proposed in this paper has strong robustness and high accuracy, which represents the initial power characteristic of P-wave and can effectively eliminate the interference of background noise.

Attention-induced semantic and boundary interaction network for camouflaged object detection

The high intrinsic similarity between camouflaged objects and the background makes camouflaged object detection (COD) more challenging than traditional salient object detection (SOD). Existing deep-learning methods often fall into the following shortcomings: (1) When dealing with high-level features, it is difficult to fully and accurately extract semantic information, which is crucial for locating camouflaged targets. (2) The camouflaged targets identified by existing methods in complex scenes have rough boundaries and incomplete spatial information. (3) Existing methods cannot effectively exert the uniqueness and complementarity of multiple features when integrating multiple features. To this end, we propose an attention-induced semantic and boundary interaction network for accurately identifying camouflaged objects. Specifically, we propose a contrastive positioning module (CPM), which adopts a contrastive learning way to separate the camouflaged object from the background, thereby obtaining the exact location of the camouflaged target and retaining more semantic information. Then, we design a boundary exploration module (BEM), which can reduce background noise interference, focus on the structural details of camouflaged targets, and explore rich fine-grained spatial information. Finally, we propose an attention-induced interaction module (AIM) to fuse multivariate information (i.e., semantic location information, boundary information, and the side output information of the backbone), and multivariate information is complementarily fused under attention guidance to generate more powerful camouflaged target features. Extensive experiments show that the proposed method on the different backbones (i.e., ResNet-50, Res2Net-50, PVTv2-B2, EfficientNet-B1) produces state-of-the-art results on several camouflaged benchmarks. The code is available https://github.com/zhangqiao970914/ASBI.

A Bearing Fault Diagnosis Method Based on Wavelet Denoising and Machine Learning

There are a lot of interference factors in the operating environment of machinery, which makes it ineffective to use traditional detection methods to judge the fault location and type of fault of the machinery, and even misjudgment of the fault location and type may occur. In order to solve these problems, this paper proposes a bearing fault diagnosis method based on wavelet denoising and machine learning. We use sensors to detect the operating conditions of rolling bearings under different working conditions to obtain datasets of different types of bearing failures. On the basis of using the wavelet denoising algorithm to reduce noise, we comprehensively evaluated five machine learning models, including K-means clustering, decision tree, random forest, and support vector machine to classify bearing faults and compare their results. By designing the fault classification evaluation prediction criteria, the following conclusions are drawn. The model proposed in this paper is significantly better than other traditional diagnostic models for bearing faults. In order to solve the problem of weak signal strength and background noise interference, this paper selects a better noise reduction algorithm under different quantitative evaluation indicators for wavelet denoising, which can better restore the true characteristics of the fault signal. Using unsupervised learning and supervised machine learning classification algorithms, the evaluation indicators before and after denoising are compared to make the classification results more accurate and reliable. This article will help researchers to intelligently diagnose the faults of rolling bearing equipment in rotating machinery.

Real-world abnormal event detection via super-resolution and few-shot learning

The performance of abnormal event detection has been greatly improved in recent years. However, due of the problems of low resolution and few labeled training samples, it is difficult to apply in practice. To address these issues, we propose a few-shot scene-adaptive abnormal event detection method. First, to restore high-quality video from low-quality video, we propose a weighted recurrent backprojection network (WRBPN). WRBPN selectively extracts supplementary information from adjacent frames based on their similarity, which is beneficial to the reconstruction of the target frame and suppresses the interference of irrelevant frames. Second, we propose an abnormal event detection network to detect abnormal events in high-quality surveillance videos. The network extracts multiscale features to obtain more discriminative representations and uses variance attention to suppress the interference of background noise. On this basis, the video frame is predicted, and abnormal event detection is performed according to the prediction error. Finally, in order to quickly adapt the model to new scenarios, we propose a metalearning-based approach. During the training process, the distribution of model parameters is learned, and the specific parameters of the model are obtained via distribution sampling. Experiments on benchmark datasets demonstrate the effectiveness of our method.

An Instance Segmentation Model Based on Deep Learning for Intelligent Diagnosis of Uterine Myomas in MRI.

Uterine myomas affect 70% of women of reproductive age, potentially impacting their fertility and health. Manual film reading is commonly used to identify uterine myomas, but it is time-consuming, laborious, and subjective. Clinical treatment requires the consideration of the positional relationship among the uterine wall, uterine cavity, and uterine myomas. However, due to their complex and variable shapes, the low contrast of adjacent tissues or organs, and indistinguishable edges, accurately identifying them in MRI is difficult. Our work addresses these challenges by proposing an instance segmentation network capable of automatically outputting the location, category, and masks of each organ and lesion. Specifically, we designed a new backbone that facilitates learning the shape features of object diversity, and filters out background noise interference. We optimized the anchor box generation strategy to provide better priors in order to enhance the process of bounding box prediction and regression. An adaptive iterative subdivision strategy ensures that the mask boundary details of objects are more realistic and accurate. We conducted extensive experiments to validate our network, which achieved better average precision (AP) results than those of state-of-the-art instance segmentation models. Compared to the baseline network, our model improved AP on the uterine wall, uterine cavity, and myomas by 8.8%, 8.4%, and 3.2%, respectively. Our work is the first to realize multiclass instance segmentation in uterine MRI, providing a convenient and objective reference for the clinical development of appropriate surgical plans, and has significant value in improving diagnostic efficiency and realizing the automatic auxiliary diagnosis of uterine myomas.

Efficient acquisition of Mueller matrix via spatially modulated polarimetry at low light field.

Mueller polarimetry performed in low light field with high speed and accuracy is important for the diagnosis of living biological tissues. However, efficient acquisition of the Mueller matrix at low light field is challenging owing to the interference of background-noise. In this study, a spatially modulated Mueller polarimeter (SMMP) induced by a zero-order vortex quarter wave retarder is first presented to acquire the Mueller matrix rapidly using only four camera shots rather than 16 shots, as in the state of the art technique. In addition, a momentum gradient ascent algorithm is proposed to accelerate the reconstruction of the Mueller matrix. Subsequently, a novel adaptive hard thresholding filter combined with the spatial distribution characteristics of photons at different low light levels, in addition to a low-pass fast-Fourier-transform filter, is utilized to remove redundant background noise from raw-low intensity distributions. The experimental results illustrate that the proposed method is more robust to noise perturbation, and its precision is almost an order of magnitude higher than that of the classical dual-rotating retarder Mueller polarimetry at low light field.