Complex Noise Environment Research Articles

A centrifugal fan blade damage identification method based on the multi-level fusion of vibro-acoustic signals and CNN

A single sensor's blade damage identification is difficult because of the complex noise environment. At the same time, the multi-source signals include complete information of fault characteristics. Aiming to effectively fuse multi-sensor signals and improve identification accuracy, a centrifugal fan blade damage identification method based on the multi-level fusion of vibro-acoustic signals and a one-dimensional convolutional neural network (1D-CNN) is proposed. Firstly, acoustic and vibration signals are fused at the data level respectively by a data-adaptive synchronization weighted fusion algorithm. Secondly, the proposed 1D-CNN network extracts feature from the fused acoustic and vibration signals. Finally, the extracted features are fused by a fully connected layer. The experimental results show that the proposed method achieves 100% recognition accuracy at four speeds. By analyzing different signal to noise ratios (SNR), this method has higher diagnostic accuracy and better robustness compared with single sensor, single-level fusion, and other diagnostic methods.

I-WKNN: Fast-speed and high-accuracy WIFI positioning for intelligent sports stadiums

Based on various existing wireless fingerprint location algorithms in intelligent sports venues, a high-precision and fast indoor location algorithm improved weighted k-nearest neighbor (I-WKNN) is proposed. In order to meet the complex environment of sports venues and the demand of high-speed sampling, this paper proposes an AP selection algorithm for offline and online stages. Based on the characteristics of the signal intensity distribution in intelligent venues, an asymmetric Gaussian filter algorithm is proposed. This paper introduces the application of the positioning algorithm in the intelligent stadium system, and completes the data acquisition and real-time positioning of the stadium. Compared with traditional WKNN and KNN algorithms, the I-WKNN algorithm has advantages in fingerprint positioning database processing, environmental noise adaptability, real-time positioning accuracy and positioning speed, etc. The experimental results show that the I-WKNN algorithm has obvious advantages in positioning accuracy and positioning time in a complex noise environment and has obvious application potential in a smart stadium.

An Improved UKF Algorithm for Extracting Weak Signals Based on RBF Neural Network

It is difficult to extract effective weak signals from complex noise environment in many engineering applications. To address the problem, an improved unscented Kalman filter (UKF) algorithm based on a radial basis function (RBF)-neural network (NN) is proposed in this paper. This algorithm achieves effective extraction of weak signals under the condition of low signal-to-noise ratio (SNR). It uses RBF-NN to establish a distributed system of state and observation models to replace the traditional UKF modeling method. Then, the RBF-NN is applied to build a constant coefficient model to modify the UKF filtering deviation value, and thus, the accuracy of the algorithm is improved. Finally, simulation experiments are conducted at different SNRs of surface nuclear magnetic resonance signals. Results show that effective weak signals can still be obtained when SNR = -10 dB, verifying the effectiveness of the algorithm.

Diffusion Generalized MCC with a Variable Center Algorithm for Robust Distributed Estimation

Classical adaptive filtering algorithms with a diffusion strategy under the mean square error (MSE) criterion can face difficulties in distributed estimation (DE) over networks in a complex noise environment, such as non-zero mean non-Gaussian noise, with the object of ensuring a robust performance. In order to overcome such limitations, this paper proposes a novel robust diffusion adaptive filtering algorithm, which is developed by using a variable center generalized maximum Correntropy criterion (GMCC-VC). Generalized Correntropy with a variable center is first defined by introducing a non-zero center to the original generalized Correntropy, which can be used as robust cost function, called GMCC-VC, for adaptive filtering algorithms. In order to improve the robustness of the traditional MSE-based DE algorithms, the GMCC-VC is used in a diffusion adaptive filter to design a novel robust DE method with the adapt-then-combine strategy. This can achieve outstanding steady-state performance under non-Gaussian noise environments because the GMCC-VC can match the distribution of the noise with that of non-zero mean non-Gaussian noise. The simulation results for distributed estimation under non-zero mean non-Gaussian noise cases demonstrate that the proposed diffusion GMCC-VC approach produces a more robustness and stable performance than some other comparable DE methods.

Single-channel speech enhancement based on joint constrained dictionary learning

To improve the performance of speech enhancement in a complex noise environment, a joint constrained dictionary learning method for single-channel speech enhancement is proposed, which solves the “cross projection” problem of signals in the joint dictionary. In the method, the new optimization function not only constrains the sparse representation of the noisy signal in the joint dictionary, and controls the projection error of the speech signal and noise signal on the corresponding sub-dictionary, but also minimizes the cross projection error and the correlation between the sub-dictionaries. In addition, the adjustment factors are introduced to balance the weight of constraint terms to obtain the joint dictionary more discriminatively. When the method is applied to the single-channel speech enhancement, speech components of the noisy signal can be more projected onto the clean speech sub-dictionary of the joint dictionary without being affected by the noise sub-dictionary, which makes the quality and intelligibility of the enhanced speech higher. The experimental results verify that our algorithm has better performance than the speech enhancement algorithm based on discriminative dictionary learning under white noise and colored noise environments in time domain waveform, spectrogram, global signal-to-noise ratio, subjective evaluation of speech quality, and logarithmic spectrum distance.

Deep‐learning‐based nuclear power plant fault detection using remote light‐emitting diode array data transmission

AbstractThis paper proposes a deep‐learning‐based wireless sensor system that uses an embedded two‐dimensional (2D) light‐emitting diode (LED) array to display measured sensor data and remote data transmission to detect nuclear power plant (NPP) equipment defects. The frequent use of electromagnetic waves often interferes with the operation of NPP. Therefore, we devised a wireless image transmission network using a 2D LED array panel that includes a sensor module and a camera to capture LED array images. Based on the experimental results, the proposed method adopting deep‐learning‐based LED array data extraction produces reliable digital data restoration performance in terms of classification accuracy, even in a complex noise environment.

Music Classification and Detection of Location Factors of Feature Words in Complex Noise Environment

In order to solve the problem of the influence of feature word position in lyrics on music emotion classification, this paper designs a music classification and detection model in complex noise environment. Firstly, an intelligent detection algorithm for electronic music signals under complex noise scenes is proposed, which can solve the limitations existing in the current electronic music signal detection process. At the same time, denoising technology is introduced to eliminate the noise and extract the features from the signal. Secondly, from the perspective of audio and lyrics of song sentiment analysis and the unique characteristics of lyrics text, a lyric sentiment analysis method based on text title and position weight is proposed. Finally, considering the influence of the weight of feature words in different positions on the classification of lyrics, the analytic hierarchy process is used to calculate the weight of feature words in different positions of text title and lyrics before, in, and after the text. The results show that in the complex noise environment, the accuracy of music classification and detection of the proposed model is more than 90%, which is far beyond the control range of the actual application of music processing. The effect of music classification and detection is better than that of the contrast model, which has a certain practical application value.

Fault detection of railway freight cars mechanical components based on multi-feature fusion convolutional neural network

The fault detection of the mechanical components in railway freight cars is important to the safety of railway transportation. Owing to the small size of the mechanical components, a manual detection method has a low detection efficiency. In addition, traditional computer vision technology has difficulty detecting multiple categories of objects simultaneously. Inspired by the use of one-stage deep-learning-based object detectors, in this paper, a multi-feature fusion network (MFF-net) for the simultaneous detection of three typical mechanical component faults is proposed. By embedding three modules in the network to improve the detection effect of small mechanical component faults, the feature fusion module is used to supplement the deep semantic information of the shallow feature maps. A multi-branch dilated convolution module uses dilated convolution and multi-branch networks to obtain the fusion features of multi-scale receptive fields, and the squeeze-and-excitation block is embedded in the network to enhance the channel features. All experiments used Nvidia 1080Ti GPUs for training on the PyTorch platform. The experimental results show that the three modules used in the network all contribute to the fault detection of railway freight car mechanical components, and that the detection performance of MFF-net is better than that of most other popular SSD-based one-stage object detectors. When the input image size is 300 pixels × 300 pixels, MFF-net can achieve 0.8872 mAP and 33 frames per second. It has good robustness to complex noise environment and can realize real-time fault detection of railway freight car mechanical components.

Research Status and Future Development of Endpoint Detection Algorithms Based on Computer Science Language Signals

Today is an information technology era, language signal recognition technology, language signal coding technology and a variety of new language technology will be widely used in all areas of our life, such as: security field, human-computer interaction, communication field. We can accurately analyze pure speech signals and silent segments in a speech by using language signal endpoint detection technology, which will bring decisive effects to the efficiency of ASR and ASC. Three steps can be used to represent the language endpoint detection model, namely, the language signal preprocessing step, the extraction of the characteristic vector of the whole language flow, and the establishment of the language endpoint discrimination model. Finally, the speech endpoint discrimination model is established. The traditional speech endpoint detection algorithms include the two threshold method based on time domain, the universal entropy method based on frequency domain and the invert characteristic method. Aiming at the low SNR and complex noise environment, in order to obtain satisfactory endpoint detection effect, this paper proposes an endpoint detection model based on optimized Extreme Learning machine (ELM), and makes up for the deficiencies of the algorithm itself by optimizing network connection parameters[1-2].

An Improved Bearing Fault Diagnosis Scheme Based on Hierarchical Fuzzy Entropy and Alexnet Network

Bearings are important part of aerospace equipments. Therefore, bearings fault diagnosis and fault detection is necessary for the safe operation. Generally, the bearing are core component and runs in a complex and heavy background noise environment. Thence, the bearing signals will be overwhelmed by noise. At present, the diagnosis methods of bearings are based on the experience of experts which costs a lot of labor and time-consuming. Consequently, to address these inadequacies, a novel method based on variational mode decomposition (VMD) algorithms and Alexnet neural network has been presented. Firstly, it decomposes the nonstationary bearing signals into intrinsic mode functions adaptively. However, background noise will seriously affect the number of signal decompositions and reduce accuracy even over-decomposition. Thence, this paper proposed the hierarchical fuzzy entropy method to adaptively extract weak fault characteristics of bearings. Then Alexnet neural network has been utilized to learn the relationship of fault features and bearings health conditions. The architecture of Alexnet diagnosis model is convenient and efficient. Finally, two tentative dataset are adopted to verify the effectiveness and feasibility of the method proposed in this article. The results show that the presented method has a higher fault diagnosis accuracy rate than traditional convolutional neural networks.

Anisotropic Diffusion Combined with Nonconvex Functional for Noise Image Segmentation

Aiming at the problems of low segmentation accuracy of noise image, poor noise immunity of the existing models and poor adaptability to complex noise environment, a noise image segmentation algorithm using anisotropic diffusion and nonconvex functional was proposed. First, focusing on the “staircase effect”, a nonconvex functional was introduced into the energy functional model for smooth denoising. Second, the validity and accuracy of the model were established by proving that there was no global minimum in the solution space of the nonconvex energy functional model; the improved model was then used to obtain a smooth and clear image edge while maintaining the edge integrity. Third, the smooth image obtained from the nonconvex energy functional model was combined with the level set model to obtain the anisotropic diffusion gray level set model. The optimal outline of the target was obtained by calculating the minimum value of the energy functional. Finally, an anisotropic diffusion equation with nonconvex energy functional model was built in this algorithm to segment noise image accurately and quickly. A series of comparative experiments on the proposed algorithm and similar algorithms were conducted. The results showed that the proposed algorithm had strong noise resistance and provided precise segmentation for noise image.

Dual-Channel Speech Enhancement Based On Speech Presence Probability

This paper introduces technology to improve sound quality, which serves the needs of media and entertainment. Major challenging problem in the speech processing applications like mobile phones, hands-free phones, car communication, teleconference systems, hearing aids, voice coders, automatic speech recognition and forensics etc., is to eliminate the background noise. Speech enhancement algorithms are widely used for these applications in order to remove the noise from degraded speech in the noisy environment. Hence, the conventional noise reduction methods introduce more residual noise and speech distortion. So, it has been found that the noise reduction process is more effective to improve the speech quality but it affects the intelligibility of the clean speech signal. In this paper, we introduce a new model of coherence-based noise reduction method for the complex noise environment in which a target speech coexists with a coherent noise around. From the coherence model, the information of speech presence probability is added to better track noise variation accurately; and during the speech presence and speech absent period, adaptive coherence-based method is adjusted. The performance of suggested method is evaluated in condition of diffuse and real street noise, and it improves the speech signal quality less speech distortion and residual noise.

Traffic State Evaluation Using Traffic Noise

Traffic state information is widely applied into all aspects of Intelligent Transportation System (ITS), such as the macro-control of government departments, the implementation of traffic managers' plans, the decision-making of residents travel, and so on. At present, Mel Frequency Cepstrum Coefficient (MFCC) is generally used as characteristic of traffic noise to characterize different traffic states, and performs well in simple noise environment, but performs poorly in complex noise environment. Based on the analysis of traffic noise acquired from a roadside-installed acoustic acquisition equipment, the evaluation problem of traffic state in complex noise environment is considered in this paper. Traffic state is divided into three categories according to traffic speed in our work: free flow (40 km/h and above), saturated flow (10-40 km/h), and jammed flow (0-10 km/h). Teager Energy Operator (TEO) is introduced to improve the MFCC characteristic, thus a novel characteristic called T-MFCC is proposed. Principal Component Analysis (PCA) is introduced to reduce dimension of T-MFCC characteristic, thus a novel characteristic called PT-MFCC is proposed. Support Vector Machine (SVM) optimized by Particle Swarm Optimization (PSO) algorithm is applied as classifier to identify traffic state. Characterization capabilities of two modified characteristics and traditional MFCC characteristic for traffic state are compared in this paper. Experimental results demonstrate that the evaluation accuracy of traffic state based on T-MFCC characteristic is 3.685% higher than that based on MFCC characteristic, and the evaluation accuracy of traffic state based on PT-MFCC characteristic is 26.466% lower than that based on MFCC characteristic. Therefore, T-MFCC characteristic is superior to MFCC characteristic, while MFCC characteristic is superior to PT-MFCC characteristic, namely, T-MFCC characteristic can better characterize traffic state than MFCC characteristic, meanwhile, there are no redundancy attributes in T-MFCC characteristic, thus PCA is not needed to reduce the dimension of T-MFCC characteristic.

Single Channel Speech Enhancement Algorithm based on BLSTM-DNN Bidirectional Optimized Hybrid Model

The performance of existing speech enhancement algorithms based on deep learning is not ideal in complex noise environment. To improve the problem, a bidirectional optimized hybrid network named BLSTM-DNN is constructed based on bidirectional long-short term memory (BLSTM) network and fully-connected deep neural network (DNN). This structure uses BLSTM to extract high-level information including past and future temporal context of noisy speech. Next, fully-connected DNN fits the high-level information to ideal ratio mask (IRM). Finally, the IRMs estimated by the BLSTM-DNN are used to enhance the noisy speech. Experimental results show that the proposed method can effectively improve the speech quality and intelligibility under unknown noise conditions.

Digital Analysis of the Vibration Signals Amplitude Spectrum Based on Fourier Processing of the Binary-Sign Analog-Stochastic Quantization Result

The article is devoted to the problem of developing a digital algorithm for operational harmonic analysis of complex vibration signals. The basis for solving this problem was the generalized equation of statistical measurements, which defines the measurement procedure as the sequential execution of interrelated measurement and computational transformations. During the development of the algorithm, special attention is paid to analog-to-digital conversion because it directly affects the computational efficiency of digital procedures for obtaining the final result. As such a conversion, the use of binarysign analog-stochastic quantization is justified, which allows performing two-level quantization without systematic error regardless of the statistical properties of the analyzed signals. The discrete-event model of the binary-sign analog-stochastic quantization result allowed for the analytical calculation of integration operations in the transition to estimating the amplitude spectrum in digital form. As a result, the developed algorithm of harmonic analysis does not require performing digital multiplication operations typical for classical algorithms, which are based on the calculation of the direct discrete Fourier transform. The execution of the algorithm is reduced to the implementation of the addition and subtraction arithmetic operations of the cosine-function values in the time moments determined by the result of the binary-sign analogue-stochastic quantization. The exclusion of digital multiplication operations provided an increase in the computational efficiency of amplitude spectrum estimation. Laboratory studies of the developed algorithm were carried out using simulation modeling. The simulation results showed that the algorithm allows calculating estimates of the amplitude spectrum of complex signals with high accuracy and frequency resolution in the presence of additive noise. In real conditions, the testing of the developed algorithm was carried out during bench studies of the operational status of the MAZ-206067 bus, designed for the transportation of passengers on urban and suburban routes of average workload. Analysis of the results of experimental studies confirmed the possibility of using the algorithm as part of the diagnosability provision for operational monitoring of vibration signals in a complex noise environment.

Multi-lead model-based ECG signal denoising by guided filter

The electrocardiogram (ECG) denoising is of paramount importance for accurate disease diagnosis, but individual differences bring great difficulties for ECG denoising, especially for Dynamic Electrocardiography (DCG). In this paper, a multi-lead model-based ECG signal denoising method is proposed, in which a guided filter is inherently adapted to denoise ECG signal. For each person, a patient-specific statistical model will be constructed by sparse autoencoder (SAE) which can effectively preserve the detailed signal features. Thus, the guided signal producing by the statistical model can perform well in the guided filter. Especially, even the sudden morphological changes, the denoised ECG signals can still be conserved. The results on the 12-lead Arrhythmia Database and the MIT-BIH Arrhythmia Database demonstrate that the signal-to-noise ratio (SNR) improvement of the proposed method can reach as high as 21.54 dB, and the mean squared error (MSE) is less than 0.0401. Besides achievement of minimum signal distortion in comparisons with the major of the current denoising algorithms for complex noise environment, the proposed method demonstrate robustness in the complex interferences, especially in tracing the sudden morphological changes of ECG signals. Due to the remarkable superiority in preserving diagnostic and detail features of ECG signals, the proposed method can handle ECG signals with abnormal heart beats, and then can improve the accuracy detection of the disease.

Multiple Radar Subbands Fusion Algorithm Based on Support Vector Regression in Complex Noise Environment

Real noise environment may not be Gaussian due to the existence of man-made interferences, natural bursts, and so on. In this paper, a new multiple radar subbands fusion algorithm in complex noise environment is proposed. The considered complex noise includes impulsive noise and the mixture of impulsive and Gaussian noises. The proposed subband fusion algorithm consists of the following steps. First, the incoherent factors are estimated and the multiple subbands are compensated to be mutually coherent. Then, coherent subbands are fit by the geometrical theory of diffraction (GTD) model, where model parameters are estimated in the frame of sparse reconstruction. Different probability distribution functions are used to describe different noise environments, and the maximum a posteriori probability (MAP) estimate of scattering model parameters is achieved. It is shown that the MAP estimate can be obtained by iteratively solving a support vector regression problem. Finally, the fused full band is obtained by extrapolating the measured subband data based on the estimated GTD model. Validity and performance of the proposed algorithm are investigated by analytical data, simulated data, and static-range data.

Speech Understanding in Noise by Patients With Cochlear Implants Using a Monaural Adaptive Beamformer.

The aim of this experiment was to compare, for patients with cochlear implants (CIs), the improvement for speech understanding in noise provided by a monaural adaptive beamformer and for two interventions that produced bilateral input (i.e., bilateral CIs and hearing preservation [HP] surgery). Speech understanding scores for sentences were obtained for 10 listeners fit with a single CI. The listeners were tested with and without beamformer activated in a "cocktail party" environment with spatially separated target and maskers. Data for 10 listeners with bilateral CIs and 8 listeners with HP CIs were taken from Loiselle, Dorman, Yost, Cook, and Gifford (2016), who used the same test protocol. The use of the beamformer resulted in a 31 percentage point improvement in performance; in bilateral CIs, an 18 percentage point improvement; and in HP CIs, a 20 percentage point improvement. A monaural adaptive beamformer can produce an improvement in speech understanding in a complex noise environment that is equal to, or greater than, the improvement produced by bilateral CIs and HP surgery.

Research on mud pulse signal detection based on adaptive stochastic resonance

The original data signals have small amplitude with a long distance signal transmission from the underground to the ground. And thousands of meters of drilling mud channel in the drilling process will contain a lot of noise sources. Therefore, the original mud pulse signals are submerged by the complex noise environment. Detecting the original signal after receiving the signal on the ground is still a serious issue. In connection with mud pulse signal detection under complex background in measurement while drilling (MWD), nonlinear bistable stochastic resonance theory and the production condition was analyzed. On the basis of this, a method of using genetic simulated annealing algorithm to adaptive optimize the parameters of stochastic resonance was proposed to realize the detection of mud pulse signal in the background of complex noise. Finally, through the simulation experiment and the field verification, this method realizes the signal detection even under the low signal-to-noise ratio (SNR). And the proposed method can overcome the shortcomings of existing detection method of signal detection performance in low SNR. It proves the proposed method's effectiveness and feasibility.

Voice activity detection in complex noise environment

Voice activity detection in complex noise environment